© 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. 130071
    Prev
    Next
    INDEX
    Explanations

    ponytails

    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
    Not in Any Lists

    No Comments

    Negative Logits
    可
    -0.08
    "]=="
    -0.07
     Herc
    -0.07
    _PROM
    -0.07
    .Sound
    -0.07
    华润
    -0.07
    "))
↵
    -0.07
     aus
    -0.07
    大战
    -0.07
     glEnable
    -0.07
    POSITIVE LOGITS
     bitmap
    0.08
    shift
    0.08
    GraphQL
    0.07
    Selector
    0.07
    command
    0.07
     redistribution
    0.07
    hton
    0.07
    (media
    0.07
     tooltip
    0.07
     datum
    0.07
    Activations Density 0.002%

    No Known Activations