© 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. 127952
    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
     maxSize
    -0.08
    ’acc
    -0.08
    filesystem
    -0.07
    _norm
    -0.07
    airs
    -0.07
     aure
    -0.07
     Pier
    -0.07
     Francisco
    -0.07
    Cele
    -0.07
    费率
    -0.07
    POSITIVE LOGITS
    _INDEX
    0.07
    躲
    0.07
    摆脱
    0.07
    影響
    0.07
          ↵↵
    0.07
    存货
    0.07
    は
    0.07
    ш
    0.07
    𝑑
    0.06
     SH
    0.06
    Activations Density 0.005%

    No Known Activations