© 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. 5303
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    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
     dio
    -0.28
     Dio
    -0.28
    Trap
    -0.27
    Recovered
    -0.27
    Reuse
    -0.27
     arbitrarily
    -0.26
    ç¨Ģ
    -0.24
     aio
    -0.24
     Stall
    -0.24
     bubb
    -0.24
    POSITIVE LOGITS
    ç«ĸ
    0.29
    Assistant
    0.27
     cord
    0.26
     EDGE
    0.26
    .jupiter
    0.26
     تØŃ
    0.26
     Help
    0.25
     rule
    0.25
     cin
    0.25
     Assistance
    0.25
    Activations Density 0.303%

    No Known Activations