© 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. 163293
    Prev
    Next
    INDEX
    Explanations

    Focusing of light/optics

    np_max-act · gemini-2.0-flash
    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
    iOS
    -0.26
    ADVERTISEMENT
    -0.26
    asta
    -0.26
    loth
    -0.26
     codes
    -0.26
    -Russian
    -0.25
     dep
    -0.25
    iola
    -0.25
    spo
    -0.24
     mixes
    -0.24
    POSITIVE LOGITS
     crystal
    0.32
    ç»ıæµİåѦ
    0.27
     kÃŃnh
    0.27
    ç»ĵæĻ¶
    0.26
    eing
    0.26
     defaultProps
    0.25
     Edge
    0.25
    累累
    0.25
    -edge
    0.25
    icie
    0.25
    Activations Density 0.006%

    No Known Activations