© 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. 15-RESID-POST-AA
    11. 55274
    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endon
    -0.07
     typeId
    -0.07
    feito
    -0.07
     thịt
    -0.07
     iParam
    -0.07
    没
    -0.07
     عليه
    -0.07
    _TBL
    -0.07
     ballots
    -0.07
     scrambling
    -0.07
    POSITIVE LOGITS
    cad
    0.07
    Boundary
    0.07
     Hoffman
    0.06
     pret
    0.06
    侂
    0.06
    教会
    0.06
    huge
    0.06
    includes
    0.06
     العلاقة
    0.06
    被迫
    0.06
    Activations Density 0.041%

    No Known Activations