© 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. 23-TRANSCODER-HP
    7. 162537
    Prev
    Next
    INDEX
    Explanations

    medical diagnoses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Attr
    -0.26
    epad
    -0.25
    astic
    -0.25
    å®Įæķ´
    -0.24
    ä¹ĭæĥħ
    -0.24
    anner
    -0.24
    CellValue
    -0.24
    container
    -0.23
     grand
    -0.23
    criptor
    -0.23
    POSITIVE LOGITS
     overlaps
    0.29
     intersections
    0.27
     resil
    0.26
     bystand
    0.26
     Disclosure
    0.25
    èĭ¦
    0.24
    markets
    0.24
    UTO
    0.24
    æľĽ
    0.24
     offended
    0.24
    Activations Density 0.006%

    No Known Activations