© 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. 107814
    Prev
    Next
    INDEX
    Explanations

    Businesses around the world

    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
    èİ«è¿ĩäºİ
    -0.35
    ä¸ŃæľĢ
    -0.28
    æľĢ容æĺĵ
    -0.28
    itious
    -0.26
    PREC
    -0.26
    æľĢå¿«
    -0.26
    æľĢå¿«çļĦ
    -0.25
    åħ¸
    -0.25
    æľĢ强
    -0.25
    类似
    -0.25
    POSITIVE LOGITS
    å»ĵ
    0.32
    ava
    0.27
    /runtime
    0.27
    æĬ¢éĻ©
    0.25
    æİ¡
    0.24
    éĩĩ
    0.23
     Felipe
    0.23
    æ³ķå¾ĭè§Ħå®ļ
    0.23
    ç´¢
    0.23
    aupt
    0.23
    Activations Density 21.119%

    No Known Activations