© 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. 5219
    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
    ĺ认
    -0.26
    iscrimination
    -0.25
    ono
    -0.24
    opper
    -0.24
    æĮģæľī人
    -0.24
    åºĸ
    -0.24
     oko
    -0.24
     homer
    -0.24
     å¿
    -0.23
    recogn
    -0.23
    POSITIVE LOGITS
    arrêt
    0.28
     Inject
    0.25
    åĪĹ
    0.25
     antenn
    0.24
    rows
    0.24
     Wanted
    0.24
     arr
    0.24
    row
    0.24
    arth
    0.24
    è¿Ľåı£
    0.24
    Activations Density 0.098%

    No Known Activations

    This feature has no known activations.