© 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. 112256
    Prev
    Next
    INDEX
    Explanations

    Math formulas

    np_max-act · gemini-2.0-flash
    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
    thus
    -0.32
     thus
    -0.28
     typingsSlinky
    -0.25
     ei
    -0.25
     patched
    -0.25
    è¿Ļæł·ä¸ĢæĿ¥
    -0.24
    çľĭä¸Ģä¸ĭ
    -0.24
    æ´µ
    -0.24
     Patch
    -0.24
    æī©æķ£
    -0.23
    POSITIVE LOGITS
    agine
    0.28
    ustin
    0.26
    æī¿æĭħ责任
    0.25
    roup
    0.25
    åĽ´ç»ķ
    0.24
    üssen
    0.24
    æ¿ĢåĬ¨
    0.24
    éĿ¢åIJij
    0.24
     wur
    0.24
    refix
    0.24
    Activations Density 0.005%

    No Known Activations