© 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. 56923
    Prev
    Next
    INDEX
    Explanations

    SQL database code

    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
    Negative Logits
    机
    -0.07
    𝅪
    -0.06
    𬭯
    -0.06
     reached
    -0.06
    Big
    -0.06
    gu
    -0.06
    澈
    -0.06
     Bord
    -0.06
    -generation
    -0.06
     unite
    -0.06
    POSITIVE LOGITS
    .scalajs
    0.07
    alık
    0.07
     #%
    0.07
    CppI
    0.07
     zarówn
    0.07
    雅
    0.07
     사람들
    0.07
    ););↵
    0.07
     ülk
    0.07
     relaxing
    0.07
    Activations Density 0.000%

    No Known Activations