© 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. 7-RESID-POST-AA
    11. 59868
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    phinx
    -0.08
    偶然
    -0.07
    秋冬
    -0.07
    /Object
    -0.07
    茚
    -0.06
    vip
    -0.06
    혐
    -0.06
    _visible
    -0.06
    atomy
    -0.06
    돕
    -0.06
    POSITIVE LOGITS
    居委会
    0.07
    阿
    0.07
     mName
    0.07
    长长
    0.06
     nale
    0.06
    .*;
↵
    0.06
    ""↵
    0.06
     ville
    0.06
    ----------
↵
    0.06
    .gif
    0.06
    Activations Density 0.261%

    No Known Activations