© 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. 108018
    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
     glu
    -0.31
    çľ¼åħī
    -0.28
    orris
    -0.28
    好æľĭåıĭ
    -0.27
    åįģæĿ¡
    -0.25
    interopRequireDefault
    -0.24
    è¾ľè´Ł
    -0.24
    俨
    -0.24
    çļĦçľ¼åħī
    -0.24
    Gate
    -0.24
    POSITIVE LOGITS
    åĴ¬
    0.29
    éĢĶ
    0.26
    ä¸įç»ı
    0.26
    -trade
    0.25
    aring
    0.25
    åħ¥
    0.24
    unate
    0.24
    гаÑĢ
    0.24
     unchecked
    0.24
    åĨ³
    0.24
    Activations Density 0.998%

    No Known Activations

    This feature has no known activations.