© 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. 162533
    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
    æĮº
    -0.30
    ANTE
    -0.28
    USED
    -0.27
    è´¢åĬĽ
    -0.26
     Cocktail
    -0.26
    EVER
    -0.24
    屯
    -0.24
    ADER
    -0.24
    第ä¸ĢæŃ¥
    -0.23
     tela
    -0.23
    POSITIVE LOGITS
    getCell
    0.32
    .createCell
    0.28
    elight
    0.27
    ework
    0.25
    ói
    0.25
     Cell
    0.25
    åľ¨ä»ĸçļĦ
    0.23
     spoon
    0.23
     Cellular
    0.23
     dig
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.