© 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. 162384
    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¦
    -0.32
    ä¸Ģ件
    -0.28
    çĶŁäº§æĢ»åĢ¼
    -0.27
     Deaths
    -0.26
    atively
    -0.25
    bots
    -0.25
    æĢ»å±Ģ
    -0.25
    ä¸Ģç»ı
    -0.24
    ç»Ļä»ĸ
    -0.24
    ÑĢÑı
    -0.24
    POSITIVE LOGITS
     match
    0.28
     vag
    0.27
    天
    0.27
    ga
    0.26
    etch
    0.26
     ust
    0.24
    idue
    0.24
    ahr
    0.24
    -match
    0.24
    æ®Ĩ
    0.24
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.