© 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. 163335
    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
    é¡¿
    -0.29
    æŃ¢
    -0.25
    常
    -0.25
    èģĶç³»
    -0.24
    åħ³ç³»
    -0.24
    ading
    -0.24
    åıĸåĨ³äºİ
    -0.24
     healthier
    -0.23
    æħĮ
    -0.23
    olith
    -0.23
    POSITIVE LOGITS
    æĬ¥è®°èĢħ
    0.26
    zano
    0.24
    åIJĦè¡Į
    0.24
    åł±
    0.24
    ovsky
    0.23
    .nativeElement
    0.23
     repost
    0.23
    SCO
    0.23
    LIN
    0.23
    åķĨæĬ¥
    0.23
    Activations Density 0.044%

    No Known Activations

    This feature has no known activations.