© 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. 5349
    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
     Chore
    -0.25
     ComVisible
    -0.25
    hk
    -0.24
     (?,
    -0.24
     #:
    -0.24
     accurately
    -0.24
    ï¼ģï¼ģ↵↵
    -0.24
    erde
    -0.24
    /weather
    -0.24
    é«ĺ度
    -0.24
    POSITIVE LOGITS
     expectancy
    0.28
    åĿIJä¸ĭ
    0.27
    æ·¼
    0.27
    æīĵæŃ»
    0.27
    par
    0.26
    _expected
    0.26
    ìĦĿ
    0.26
     expected
    0.26
    Traits
    0.25
     seating
    0.25
    Activations Density 0.156%

    No Known Activations

    This feature has no known activations.