© 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. 107816
    Prev
    Next
    INDEX
    Explanations

    Domain extensions

    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
    gue
    -0.26
    æīĺ
    -0.25
    å²ļ
    -0.25
    LES
    -0.24
    /--
    -0.24
    <>
    -0.24
    rypted
    -0.24
    annel
    -0.24
     thick
    -0.23
    çģµæĦŁ
    -0.23
    POSITIVE LOGITS
     obe
    0.29
     obey
    0.28
    å¿ĥæĦı
    0.27
    éģµå®Ī
    0.26
    åĻ¢
    0.25
    ä¸ĢåĪ»
    0.24
    åij¦
    0.24
     adhere
    0.24
    æ¼Ĥ
    0.24
    æݧåĪ¶ç³»ç»Ł
    0.24
    Activations Density 0.153%

    No Known Activations