© 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. 63892
    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
     Baths
    -0.26
    æĢ§å¼º
    -0.26
    ä¸¤å¼ł
    -0.26
    æ´ĭæ´ĭ
    -0.24
    AGENT
    -0.24
    çļĦåħ³ç³»
    -0.24
    лик
    -0.24
    AndView
    -0.24
    罨
    -0.24
    æĢ§çĸ¾çĹħ
    -0.24
    POSITIVE LOGITS
    oy
    0.28
     fair
    0.28
    ût
    0.28
    åIJĮæľŁ
    0.26
     Soon
    0.26
    è¿Ļ个åIJįåŃĹ
    0.26
    èµĭ
    0.25
     Amb
    0.24
    mez
    0.24
    UBE
    0.24
    Activations Density 8.182%

    No Known Activations

    This feature has no known activations.