© 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. 25-TRANSCODER-HP
    7. 107918
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¨įç¨į
    -0.28
    æľīæīĢ
    -0.26
    è·¨çķĮ
    -0.25
    arbonate
    -0.24
    .contents
    -0.24
    .nodeType
    -0.24
     Mason
    -0.23
    åĶł
    -0.23
    inally
    -0.23
    BarItem
    -0.23
    POSITIVE LOGITS
     Hoch
    0.27
     disappearing
    0.26
     exponential
    0.26
     unreasonable
    0.25
    cloak
    0.25
    ç½ijé¦ĸ页
    0.25
    ä¸įåĬ¨
    0.24
    æĽ´ä½İ
    0.24
    ç±į
    0.24
    /+
    0.24
    Activations Density 0.150%

    No Known Activations