© 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. 11-RESID-POST-AA
    11. 72043
    Prev
    Next
    INDEX
    Explanations

    changes, replacements

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    hh
    -0.07
    etchup
    -0.07
    father
    -0.07
    .....
    -0.07
    民营
    -0.07
    азв
    -0.06
    分工
    -0.06
    start
    -0.06
     tense
    -0.06
    ()):↵
    -0.06
    POSITIVE LOGITS
     Lore
    0.08
     الحديد
    0.08
     Ged
    0.08
    graphs
    0.07
    ﺀ
    0.07
     nozzle
    0.07
    們
    0.07
    وار
    0.07
    foil
    0.07
    oulder
    0.07
    Activations Density 0.047%

    No Known Activations