© 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. 5358
    Prev
    Next
    INDEX
    Explanations

    Medical treatments/prevention/agriculture

    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
     globally
    -0.28
    -global
    -0.25
     screens
    -0.25
    faq
    -0.25
     dup
    -0.24
    morgan
    -0.24
    sector
    -0.23
    çļĦç¡®
    -0.23
    -ass
    -0.23
     zb
    -0.23
    POSITIVE LOGITS
    dling
    0.28
    rit
    0.26
    rc
    0.25
    缨
    0.25
    åIJĬ
    0.25
    åįij
    0.25
    NECT
    0.24
     skirts
    0.24
    çĶŁçĶŁ
    0.24
    möglich
    0.24
    Activations Density 0.030%

    No Known Activations