© 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 EvalsExportsAPI 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. 112979
    Prev
    Next
    INDEX
    Explanations

    provide

    np_max-act · gemini-2.0-flash

    tokens asking about the assistant itself (identity, model, capabilities, or knowledge/knowledge-cutoff).

    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
    _Stop
    -0.08
    achelor
    -0.08
    욝
    -0.07
    ┎
    -0.07
     desperate
    -0.07
    utsche
    -0.07
    骠
    -0.07
    솝
    -0.07
    סוף
    -0.07
     Direct
    -0.07
    POSITIVE LOGITS
     FIG
    0.07
     navigate
    0.07
    承载
    0.07
     tty
    0.07
     Key
    0.07
     enclave
    0.07
     McA
    0.06
    电子信息
    0.06
     attributable
    0.06
    塔
    0.06
    Activations Density 0.490%

    No Known Activations