© 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. 76400
    Prev
    Next
    INDEX
    Explanations

    short, often two-letter CamelCase or capitalized fragments within proper names, acronyms, and code identifiers.

    oai_token-act-pair · gpt-5Triggered 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
    每当
    -0.07
    getting
    -0.07
    Father
    -0.07
     bans
    -0.06
    generated
    -0.06
    ceptions
    -0.06
     saldır
    -0.06
     che
    -0.06
    oto
    -0.06
    不可
    -0.06
    POSITIVE LOGITS
     calorie
    0.08
    .What
    0.07
     TMP
    0.07
    ITIZE
    0.07
    Factors
    0.07
     questioned
    0.07
     compiling
    0.07
    -Class
    0.07
    _barrier
    0.07
    _mc
    0.06
    Activations Density 0.208%

    No Known Activations