© 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. 19-TRANSCODER-HP
    7. 5807
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     himself
    -0.34
    INDER
    -0.33
    PLY
    -0.29
     herself
    -0.28
    ply
    -0.27
    尺度
    -0.26
    PLIER
    -0.26
    æĦŁ
    -0.25
    cly
    -0.25
    ä»ĸåľ¨
    -0.24
    POSITIVE LOGITS
    onaut
    0.28
    ature
    0.27
    erves
    0.26
     schedules
    0.24
    erg
    0.24
    bos
    0.24
    ...',
    0.24
    åŃ½
    0.24
     Acceler
    0.23
    erve
    0.23
    Activations Density 0.090%

    No Known Activations

    This feature has no known activations.