© 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. 22-TRANSCODER-HP
    7. 111334
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oren
    -0.29
     Days
    -0.28
    //=
    -0.24
    æĹ¥è®¯
    -0.24
    adow
    -0.23
    EQ
    -0.23
    ç¨ĭå¼ı
    -0.23
    ä¸ĢæĹı
    -0.22
    adas
    -0.22
    OfFile
    -0.22
    POSITIVE LOGITS
    world
    0.27
    æ³ķå®ļ
    0.27
    ä»ĸçŁ¥éģĵ
    0.26
     pea
    0.25
     pup
    0.25
    ystate
    0.24
    她说
    0.24
    ded
    0.24
    typ
    0.24
    thumbs
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.