© 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. 162633
    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
    æĬ¥å¤į
    -0.26
    eneg
    -0.25
    èĥ¼
    -0.25
    举æĸ¹
    -0.25
     unheard
    -0.25
    ç»Ħç»ĩ
    -0.25
    Assert
    -0.24
     skin
    -0.24
     sys
    -0.24
     salute
    -0.24
    POSITIVE LOGITS
     galer
    0.26
    ä¸įåı¯éģ¿åħį
    0.26
    .isBlank
    0.26
    Else
    0.25
    çļĦæĹ¶ä»£
    0.25
    çļĦåIJĮåѦ
    0.25
    交æ±ĩ
    0.25
    çļĦæľĭåıĭ
    0.24
    æīįæľī
    0.24
    çļĦæĥħ
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.