© 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. 63591
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    âĢ¦”↵↵
    -0.32
    âĢ¦↵↵↵↵
    -0.30
    ,âĢ¦↵↵
    -0.28
    aire
    -0.27
    obic
    -0.27
    åľ¨çݩ家
    -0.26
    ,Th
    -0.26
    cÃŃ
    -0.26
    ,↵↵↵↵
    -0.26
    âĢ¦”
    -0.26
    POSITIVE LOGITS
    shot
    0.29
    ä¸įåģľ
    0.29
    å³ģ
    0.27
    èĢĮæĿ¥
    0.27
    代è¨Ģ
    0.26
     shot
    0.26
    ä¸įå°½
    0.25
    ä¸įæĸŃåĪĽæĸ°
    0.25
    并åIJij
    0.25
    4
    0.25
    Activations Density 8.230%

    No Known Activations