© 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. 5941
    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
     manslaughter
    -0.25
    ç»ĦåĽ¾
    -0.24
     bare
    -0.24
     seventy
    -0.24
     sevent
    -0.24
     seventeen
    -0.24
    Feat
    -0.24
    BarButton
    -0.23
     Trib
    -0.23
     RedirectTo
    -0.23
    POSITIVE LOGITS
    ialis
    0.29
    esting
    0.27
    ported
    0.25
    éĤ£ä¸ª
    0.24
    mie
    0.24
    vang
    0.24
    inde
    0.24
    Ng
    0.24
    éĢĨ
    0.24
    ster
    0.23
    Activations Density 0.879%

    No Known Activations

    This feature has no known activations.