© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 82860
    Prev
    Next
    INDEX
    Explanations

    Wishes and deals

    np_max-act · gemini-2.0-flash

    references to wishes or wish-granting bargains (genie/fairy deals and their costs or consequences) in a fairy‑tale narrative.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     пит
    -0.07
    ListComponent
    -0.07
     잘
    -0.07
     сек
    -0.07
     fighters
    -0.07
     {{--<
    -0.07
    再一次
    -0.07
    programming
    -0.06
     sophistication
    -0.06
    💍
    -0.06
    POSITIVE LOGITS
     Peak
    0.08
     vüc
    0.08
    외
    0.08
     weakened
    0.07
    Really
    0.07
    硗
    0.07
    .threshold
    0.07
     Expenses
    0.07
    ACY
    0.07
    ,count
    0.07
    Activations Density 0.044%

    No Known Activations