© 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. 107569
    Prev
    Next
    INDEX
    Explanations

    question

    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
    è¿Ļç¯ĩ
    -0.28
    è¿Ļ个èģĮä¸ļ
    -0.27
    CCI
    -0.27
    apter
    -0.26
     Powered
    -0.26
     Ala
    -0.26
    incy
    -0.25
    缸è§ģ
    -0.25
    .Listener
    -0.25
    çļĦåIJĪä½ľ
    -0.25
    POSITIVE LOGITS
    æĢ»ç»ĵ
    0.32
    -summary
    0.28
     summary
    0.27
    hist
    0.27
    -modal
    0.25
    æīĢéľĢ
    0.25
    omb
    0.24
     quiet
    0.24
     summar
    0.24
    _AUTHOR
    0.24
    Activations Density 1.490%

    No Known Activations