© 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. 163326
    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
    cai
    -0.31
    _derivative
    -0.29
    acia
    -0.28
    ä¸ĬæĿ¥
    -0.27
     yourselves
    -0.26
     der
    -0.26
     yours
    -0.25
     yourself
    -0.25
     begging
    -0.24
    ÑģÑĭл
    -0.24
    POSITIVE LOGITS
     Liter
    0.26
    çݯç»ķ
    0.26
     Incre
    0.26
    -liter
    0.25
    istar
    0.25
    ard
    0.25
     Nichols
    0.24
    ç¹ģæ®ĸ
    0.24
     Stevens
    0.24
    itage
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.