© 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. 19-RESID-POST-AA
    11. 127955
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Ray
    -0.08
    ච
    -0.08
    ographical
    -0.07
    妮
    -0.07
    acia
    -0.07
     hann
    -0.07
    鐘
    -0.07
    باح
    -0.07
     î
    -0.07
    动机
    -0.07
    POSITIVE LOGITS
    projectId
    0.07
    脒
    0.07
    一大批
    0.07
    最大程度
    0.07
    管理体系
    0.07
    -LAST
    0.07
    _moves
    0.07
    UserProfile
    0.07
    心理学
    0.07
    RS
    0.07
    Activations Density 0.002%

    No Known Activations