© 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. 108433
    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
     Drum
    -0.30
    ilate
    -0.27
    è¿Ŀç«ł
    -0.26
    è¿ĺæĺ¯
    -0.26
    ograms
    -0.26
    èħĬ
    -0.25
    \Mapping
    -0.25
    é¼ĵ
    -0.24
    çļĦæł·åŃIJ
    -0.24
    ä½ľæģ¯
    -0.24
    POSITIVE LOGITS
    AINS
    0.28
     SPL
    0.27
     transactions
    0.26
    ä¼ģä¸ļæıIJä¾Ľ
    0.25
     finance
    0.25
    íķľëĭ¤ë©´
    0.25
    å¹´ä¹ĭ
    0.25
    ucid
    0.25
    eger
    0.25
    è¿Ļ份
    0.24
    Activations Density 0.236%

    No Known Activations

    This feature has no known activations.