© 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. 20-TRANSCODER-HP
    7. 141446
    Prev
    Next
    INDEX
    Explanations

    software licensing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įåĪ©
    -0.29
    éģĩ
    -0.25
     infinitely
    -0.24
     Inf
    -0.24
    .sponge
    -0.24
     rè
    -0.23
     Din
    -0.23
     Anthem
    -0.23
     Federation
    -0.23
    åħ¨è¿ĩç¨ĭ
    -0.23
    POSITIVE LOGITS
    /close
    0.31
     RES
    0.28
     MART
    0.25
    æĹłè®ºå¦Ĥä½ķ
    0.25
     RET
    0.25
     CLOSE
    0.25
    æĥ¯
    0.24
     Retrie
    0.24
     familia
    0.24
     Complete
    0.23
    Activations Density 3.476%

    No Known Activations