© 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. 12009
    Prev
    Next
    INDEX
    Explanations

    on

    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
    Not in Any Lists

    No Comments

    Negative Logits
    😠
    -0.09
    Markers
    -0.07
     Fri
    -0.07
    𝜂
    -0.07
    iterations
    -0.07
    .PORT
    -0.06
    可用
    -0.06
     תודה
    -0.06
    [
    -0.06
    .innerHeight
    -0.06
    POSITIVE LOGITS
    腔
    0.08
     yan
    0.07
     dint
    0.07
    老牌
    0.07
     wym
    0.06
     HIV
    0.06
    篾
    0.06
    服装
    0.06
    점
    0.06
    /{}/
    0.06
    Activations Density 0.003%

    No Known Activations