© 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. 129650
    Prev
    Next
    INDEX
    Explanations

    where

    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
    讽
    -0.27
    驶
    -0.27
    ë´ī
    -0.26
    center
    -0.25
    æ¼²
    -0.24
    (center
    -0.24
    ________________
    -0.24
    åľĴ
    -0.23
    ance
    -0.22
    ewhere
    -0.22
    POSITIVE LOGITS
    uchos
    0.29
    ä½ķå¿ħ
    0.27
    ynch
    0.26
     Nhi
    0.26
    wish
    0.25
    è¿Ļ两ç§į
    0.25
    ä¸įèĪį
    0.25
    aturas
    0.25
    URITY
    0.25
    hecy
    0.24
    Activations Density 9.190%

    No Known Activations