© 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. 79354
    Prev
    Next
    INDEX
    Explanations

    "check"

    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
    选项
    -0.07
    ခ
    -0.07
    .Property
    -0.07
     complicated
    -0.06
    国情
    -0.06
     reconcile
    -0.06
     akt
    -0.06
     dotyczą
    -0.06
     odby
    -0.06
     Comple
    -0.06
    POSITIVE LOGITS
    (Log
    0.08
    _VERIFY
    0.07
    _star
    0.07
    urrency
    0.07
     lastIndex
    0.07
    Unknown
    0.07
    =Value
    0.07
    Driver
    0.07
     Rubber
    0.07
     Narc
    0.07
    Activations Density 0.023%

    No Known Activations