© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43477
    Prev
    Next
    INDEX
    Explanations

    becoming involved

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imming
    -0.28
    fov
    -0.28
    æ·±
    -0.27
     dense
    -0.27
    深深çļĦ
    -0.27
     deep
    -0.27
    Deep
    -0.26
    èĹı
    -0.26
     upon
    -0.25
     worth
    -0.25
    POSITIVE LOGITS
     draw
    0.29
    æ»ŀåIJİ
    0.29
    wise
    0.29
    æľŃ
    0.27
     involved
    0.27
     nationally
    0.27
    .Identity
    0.26
    draw
    0.26
    .nasa
    0.26
     draws
    0.26
    Activations Density 0.002%

    No Known Activations