© 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. 108969
    Prev
    Next
    INDEX
    Explanations

    supporting information files

    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
     restitution
    -0.32
     rects
    -0.27
    chai
    -0.26
    isque
    -0.24
    ãģ£ãģ±
    -0.24
    >y
    -0.24
    好æ¶Īæģ¯
    -0.24
     palms
    -0.23
    ponsive
    -0.23
     regenerated
    -0.23
    POSITIVE LOGITS
    å¤ĸçķĮ
    0.29
     Outs
    0.27
    ä¸ĭ游
    0.26
    ä¸ĢåįĬ
    0.25
    å¾Īå¤ļ
    0.25
    åħ¨æĸĩ
    0.25
    èŀįåIJĪ
    0.24
    å¤ĸéĿ¢
    0.24
    Pat
    0.24
    hots
    0.24
    Activations Density 0.898%

    No Known Activations