© 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. 43308
    Prev
    Next
    INDEX
    Explanations

    say "throw"

    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
    bcm
    -0.30
     hud
    -0.25
    mousemove
    -0.24
     Böl
    -0.24
     Hib
    -0.24
    黼
    -0.24
    笺
    -0.24
    erset
    -0.23
    llib
    -0.23
    åĩºå·®
    -0.23
    POSITIVE LOGITS
     throw
    0.72
     throwing
    0.69
    æĬĽ
    0.67
    æĬķ
    0.66
    throw
    0.63
     throws
    0.63
    丢
    0.63
    Throw
    0.62
     Throw
    0.62
    æīĶ
    0.62
    Activations Density 0.000%

    No Known Activations