© 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. 83217
    Prev
    Next
    INDEX
    Explanations

    m

    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
    hits
    -0.08
    @a
    -0.07
    ⦁
    -0.07
    .Build
    -0.07
     Price
    -0.07
     curiosity
    -0.07
    .multi
    -0.07
    .statusCode
    -0.07
     addresses
    -0.07
    speed
    -0.07
    POSITIVE LOGITS
    rael
    0.07
    _FORM
    0.07
    RAINT
    0.06
    缓缓
    0.06
     DOJ
    0.06
    傩
    0.06
    锹
    0.06
    _scal
    0.06
    _TRANS
    0.06
     Survivor
    0.06
    Activations Density 0.348%

    No Known Activations