© 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. 130412
    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
    å¼ı
    -0.31
    atal
    -0.30
    isable
    -0.30
    ivic
    -0.29
    åħ±
    -0.28
     ------------------------------------------------------------------------↵
    -0.27
    odynam
    -0.26
    çĶ³è¯ī
    -0.26
     Debug
    -0.26
     hit
    -0.25
    POSITIVE LOGITS
    DataTask
    0.28
    utures
    0.26
    stractions
    0.26
    éļĶçĿĢ
    0.25
    è¿ľç¨ĭ
    0.25
    <SpriteRenderer
    0.24
    åħĨ
    0.24
     Gesture
    0.24
    Considering
    0.24
     ControllerBase
    0.24
    Activations Density 0.181%

    No Known Activations

    This feature has no known activations.