© 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. 149520
    Prev
    Next
    INDEX
    Explanations

    Canada related

    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
    åıŃ
    -0.26
     Farr
    -0.26
    tant
    -0.26
    踢
    -0.25
    è¢Ī
    -0.25
     coded
    -0.25
     Dodd
    -0.25
     gel
    -0.24
    ä½
    -0.24
    phia
    -0.24
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.78
     Canadians
    0.71
     Canada
    0.67
     Toronto
    0.66
    åĬłæĭ¿
    0.66
     Canadian
    0.65
    Canada
    0.64
     RCMP
    0.63
    Canadian
    0.62
    Toronto
    0.62
    Activations Density 1.531%

    No Known Activations