© 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. 130784
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     ado
    -0.29
    inear
    -0.28
    éļı便
    -0.27
     Anyway
    -0.26
    addy
    -0.26
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.26
     anyway
    -0.25
    ump
    -0.25
    OrUpdate
    -0.25
    ipline
    -0.25
    POSITIVE LOGITS
    åĽłä¸º
    0.33
     because
    0.33
    MIT
    0.33
    because
    0.29
    åĽłä¸ºå¥¹
    0.29
     MIT
    0.28
     porque
    0.28
    åĽłä¸ºä»ĸ
    0.28
     perchè
    0.28
    its
    0.27
    Activations Density 0.043%

    No Known Activations