Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 11-TRANSCODER-HP
    4. 65851
    Prev
    Next
    INDEX
    Explanations

    clever

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     personality
    -0.28
     Personality
    -0.28
     staging
    -0.26
    olib
    -0.25
    åģļè¿ĩ
    -0.25
    åijĺ
    -0.24
    agi
    -0.24
    大家
    -0.24
    Traits
    -0.24
    åIJĮäºĭ
    -0.24
    POSITIVE LOGITS
    ä»ħ代表
    0.31
     sino
    0.26
    çļĦå±ĢéĿ¢
    0.26
    第ä¸ĢæĿ¡
    0.25
    ä¹Łä¸įæķ¢
    0.25
     sondern
    0.25
    æĹłç¼ĺ
    0.25
    semb
    0.25
    ç»ıæµİæĬĢæľ¯
    0.25
     Guth
    0.24
    Activations Density 0.034%

    No Known Activations