© 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. 162421
    Prev
    Next
    INDEX
    Explanations

    Code and website disclaimers

    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
    >w
    -0.29
    ç°ª
    -0.27
    æķħ
    -0.27
     bure
    -0.27
    curve
    -0.26
    èİ·å¾ĹæĽ´å¤ļ
    -0.26
    碾
    -0.26
    <w
    -0.26
    以æĿ¥
    -0.26
     privé
    -0.25
    POSITIVE LOGITS
     Display
    0.33
     displays
    0.30
     display
    0.28
    isplay
    0.28
    vara
    0.28
    Display
    0.27
     displayed
    0.27
    display
    0.27
    croll
    0.26
     displaying
    0.25
    Activations Density 0.007%

    No Known Activations