© 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. 163823
    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
    ç¨į
    -0.31
     moderated
    -0.29
    çķ¥
    -0.28
    西éĥ¨
    -0.26
    çķ¥æľī
    -0.25
    eric
    -0.25
     slightly
    -0.25
    çķ¥å¾®
    -0.24
    è¾ĥ为
    -0.24
    cu
    -0.24
    POSITIVE LOGITS
    åŁķ
    0.30
    ষ
    0.28
    å·¡éĢ»
    0.27
    æİĴæ°´
    0.25
     prze
    0.24
    çīĪæĿĥ
    0.24
     meis
    0.24
     Rd
    0.23
    quired
    0.23
     gratuita
    0.23
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.