© 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. 163800
    Prev
    Next
    INDEX
    Explanations

    this

    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
    éĤ£æ¬¡
    -0.30
    ä»ĬåĽŀãģ¯
    -0.28
    æĸĩç«łæĿ¥æºIJ
    -0.28
    款
    -0.28
     scholarship
    -0.28
    mars
    -0.25
    èīº
    -0.25
     Essays
    -0.25
     news
    -0.25
     Zot
    -0.24
    POSITIVE LOGITS
    æĪij们çļĦ
    0.28
    oco
    0.28
     heels
    0.28
     Äijá»ķ
    0.26
    æķ´ä¸ª
    0.26
    æĶ¾æĺł
    0.25
    umps
    0.25
    åħĪ
    0.25
    èħ°
    0.25
    ä½ĵ温
    0.24
    Activations Density 0.004%

    No Known Activations