© 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. 5250
    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
    emann
    -0.29
     inf
    -0.25
    .GetItem
    -0.25
    åĪ«
    -0.25
     coils
    -0.25
    rolley
    -0.25
    .Variable
    -0.24
    annt
    -0.24
    ma
    -0.24
     variable
    -0.24
    POSITIVE LOGITS
    çŁŃæľŁ
    0.28
     Bhar
    0.28
    æļĤç¼ĵ
    0.26
    uptime
    0.25
    æ°§
    0.25
     Kidd
    0.25
     Breath
    0.25
    opard
    0.24
    æ¯Ļ
    0.24
    emploi
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.