© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11-RESID-POST-AA
    11. 57261
    Prev
    Next
    INDEX
    Explanations

    sklearn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;">↵
    -0.08
    mpeg
    -0.07
    戢
    -0.07
     flourish
    -0.07
    戋
    -0.06
    ifold
    -0.06
    העבר
    -0.06
    /inet
    -0.06
    愁
    -0.06
    _mC
    -0.06
    POSITIVE LOGITS
    (profile
    0.08
    _SIGN
    0.07
    woods
    0.07
    Sites
    0.07
    innacle
    0.07
     deliber
    0.07
    grey
    0.07
     Ultr
    0.07
    ZERO
    0.07
    読
    0.07
    Activations Density 0.003%

    No Known Activations