© 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. 107958
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    umeric
    -0.29
    ä¸įä¸Ĭ
    -0.26
     asset
    -0.26
    âĢ¦↵↵↵
    -0.26
    æ±ģ
    -0.26
    mite
    -0.25
    âĢ¦”↵↵
    -0.24
     ÑĤÑĥ
    -0.24
    åĽŀåIJĪ
    -0.24
    åIJı
    -0.24
    POSITIVE LOGITS
     Dipl
    0.29
    åıĹæįŁ
    0.25
    å¥Ħ
    0.24
    pek
    0.24
    åıĹå½±åĵį
    0.24
    abl
    0.24
    iki
    0.23
    åŃº
    0.23
    ifold
    0.23
    ypse
    0.23
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.