© 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. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 151123
    Prev
    Next
    INDEX
    Explanations

    Canada

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Farr
    -0.28
     Delegate
    -0.27
     newPos
    -0.26
    -coded
    -0.26
    agues
    -0.26
     SPL
    -0.25
    ague
    -0.25
    éĺ¡
    -0.24
    coded
    -0.24
    Delegate
    -0.24
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.75
     Toronto
    0.63
     Canadians
    0.63
    Canadian
    0.62
     Canadian
    0.62
     Canada
    0.60
     RCMP
    0.59
    Canada
    0.58
    Toronto
    0.58
     Trudeau
    0.57
    Activations Density 0.916%

    No Known Activations