© 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. 23-TRANSCODER-HP
    7. 25235
    Prev
    Next
    INDEX
    Explanations

    Hosting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĬĢ
    -0.28
    indows
    -0.27
    _formats
    -0.26
    ensch
    -0.26
     pari
    -0.25
     Rolls
    -0.25
    fontName
    -0.24
    åħ¶ä»ĸ
    -0.24
     other
    -0.24
    inox
    -0.24
    POSITIVE LOGITS
    为åķ¥
    0.26
     #č↵
    0.25
    羣å¿ĥ
    0.25
     Integration
    0.24
    ãģªãģľ
    0.24
     housing
    0.24
    č↵č↵č↵č↵
    0.24
    åį´è¢«
    0.23
    ведение
    0.23
    è¶ĬæĿ¥è¶Ĭå°ij
    0.23
    Activations Density 0.038%

    No Known Activations