© 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. 130390
    Prev
    Next
    INDEX
    Explanations

    Diarrhea and treatments

    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
     vomiting
    -0.08
    全流程
    -0.07
     Lightning
    -0.07
    期权
    -0.07
     scooter
    -0.07
    atti
    -0.07
    umbotron
    -0.07
    Nullable
    -0.07
    攻坚战
    -0.07
    .ToolStripMenuItem
    -0.07
    POSITIVE LOGITS
    𝗸
    0.07
     esper
    0.07
     She
    0.07
    ぴ
    0.07
    sehen
    0.06
    :"↵
    0.06
    -br
    0.06
    HEY
    0.06
    patches
    0.06
     sequelize
    0.06
    Activations Density 0.037%

    No Known Activations