© 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. 64317
    Prev
    Next
    INDEX
    Explanations

    computing/finance

    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
    uits
    -0.32
    uit
    -0.29
     useStyles
    -0.29
    对ä»ĺ
    -0.28
    ificate
    -0.27
    chwitz
    -0.26
     against
    -0.25
    çĪµå£«
    -0.25
    Against
    -0.25
    emens
    -0.25
    POSITIVE LOGITS
    浪
    0.28
    é¼į
    0.27
    符åIJĪæĿ¡ä»¶
    0.27
    åĩºçİ°
    0.26
    æ¿ł
    0.26
    éĢģä¸Ĭ
    0.25
    è¶Ĭ好
    0.24
    éĻ¢åŃIJ
    0.24
    橹
    0.24
    çĽ¸å·®
    0.23
    Activations Density 24.090%

    No Known Activations