© 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. 163140
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    sum
    -0.34
     sum
    -0.32
    éĿ¢ç§¯çº¦
    -0.30
    æĢ»éĿ¢ç§¯
    -0.30
    ä¸Ģ段
    -0.29
    (sum
    -0.29
    æķ´ä¸ª
    -0.28
    -sum
    -0.28
     portions
    -0.28
    -percent
    -0.28
    POSITIVE LOGITS
     numberOf
    0.40
     fewer
    0.38
    æķ°éĩı
    0.37
    æķ°çĽ®
    0.37
    numberOf
    0.35
     numbered
    0.34
     numbering
    0.33
    NumberOf
    0.33
     NumberOf
    0.33
     count
    0.32
    Activations Density 0.001%

    No Known Activations