© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162455
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shield
    -0.28
    auge
    -0.28
    avy
    -0.28
    cut
    -0.25
    è®¤çľŁåŃ¦ä¹ł
    -0.25
    entication
    -0.24
    æĸ°å¸¸æĢģ
    -0.24
    anium
    -0.24
    娲
    -0.24
     paraph
    -0.23
    POSITIVE LOGITS
    iju
    0.34
    纯
    0.25
    ç®±åŃIJ
    0.24
    è¢ĭåŃIJ
    0.24
    è¢ĭ
    0.24
    atra
    0.24
    _except
    0.23
    pur
    0.23
    ¢
    0.23
    nas
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.