© 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. 130630
    Prev
    Next
    INDEX
    Explanations

    that

    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
    front
    -0.27
    ä»·æł¼
    -0.27
    (front
    -0.27
    azar
    -0.26
    Front
    -0.25
    åīį端
    -0.25
    é¦ĸåĪĽ
    -0.24
    ä¸įå¾Ĺä¸į
    -0.24
     caucus
    -0.24
    åĽłæŀľ
    -0.24
    POSITIVE LOGITS
    åIJ¬å¾Ĺ
    0.27
     PIE
    0.25
    æľIJ
    0.25
    arness
    0.24
    ÑģлÑĥÑĪа
    0.23
     ########################################################################
    0.23
     modifiers
    0.22
     specialties
    0.22
    locking
    0.22
     books
    0.22
    Activations Density 0.013%

    No Known Activations