© 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. 20-TRANSCODER-HP
    7. 108227
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    år
    -0.32
    éĻ¸
    -0.27
    /OR
    -0.27
    lands
    -0.27
    éĻĨ
    -0.25
    绦
    -0.24
    land
    -0.24
    ted
    -0.24
    Duplicate
    -0.24
    èĻ±
    -0.24
    POSITIVE LOGITS
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.27
    ä¸įåIJĪçIJĨ
    0.26
     ball
    0.26
     Panther
    0.26
     mãi
    0.25
    æĸ°æĿIJæĸĻ
    0.25
    éļĶ
    0.25
     usually
    0.25
     material
    0.24
     actual
    0.24
    Activations Density 1.479%

    No Known Activations

    This feature has no known activations.