© 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. 111985
    Prev
    Next
    INDEX
    Explanations

    Math questions and answers

    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
    å¾Īæĸ¹ä¾¿
    -0.28
    appoint
    -0.27
    强æľīåĬĽçļĦ
    -0.26
    nan
    -0.25
     Byrne
    -0.25
    éķ¿å¾Ĺ
    -0.25
    .mvp
    -0.24
    å¾Īæĺ¯
    -0.24
    илÑĮ
    -0.24
    -members
    -0.24
    POSITIVE LOGITS
    ä½Ĩè¿Ļ
    0.42
     but
    0.42
    ä¸įè¿ĩ
    0.39
     though
    0.38
    ä½ĨæĪij们
    0.37
    ä½Ĩ
    0.37
    but
    0.36
    èĻ½çĦ¶
    0.36
     although
    0.35
    ä½Ĩä»İ
    0.35
    Activations Density 0.010%

    No Known Activations