© 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. 59732
    Prev
    Next
    INDEX
    Explanations

    vi

    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
    Č
    -0.08
    _ALERT
    -0.07
    ’in
    -0.07
    ieder
    -0.07
    Ś
    -0.07
    angen
    -0.07
    웽
    -0.07
    ˌ
    -0.07
    obi
    -0.07
     Bombay
    -0.07
    POSITIVE LOGITS
    旗舰店
    0.08
    :@""
    0.08
     BaseActivity
    0.07
    �
    0.07
     userDao
    0.07
     haircut
    0.07
    消息称
    0.07
     fac
    0.07
    �
    0.07
    反腐倡
    0.07
    Activations Density 0.005%

    No Known Activations