© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149155
    Prev
    Next
    INDEX
    Explanations

    Company/brand names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĮĹ京大åѦ
    -0.27
     acts
    -0.27
     Acting
    -0.26
    è¯ķè¯ķ
    -0.26
    drawing
    -0.24
    .library
    -0.24
    emy
    -0.24
    proto
    -0.24
     himself
    -0.23
    ä¸ĩè¾Ĩ
    -0.23
    POSITIVE LOGITS
    ernote
    0.29
     Held
    0.28
     Falk
    0.26
     Fortune
    0.26
    åľ¨åħ¨çIJĥ
    0.26
     Benton
    0.25
    Nach
    0.25
    inject
    0.25
    annes
    0.24
    贯穿
    0.24
    Activations Density 0.138%

    No Known Activations