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. 47283
    Prev
    Next
    INDEX
    Explanations

    code testing

    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
     unlucky
    -0.26
    IFI
    -0.26
    亿ä¸ĩ
    -0.26
    abet
    -0.25
    bable
    -0.25
    ç¼Ŀ
    -0.25
    æĸ°æĪ¿
    -0.24
    FINE
    -0.24
    ulado
    -0.24
    .openConnection
    -0.24
    POSITIVE LOGITS
    è§Ħæł¼
    0.26
     cgi
    0.26
    rip
    0.25
     affiliate
    0.25
    æĿ¥ä¸´
    0.25
    ainer
    0.25
     игÑĢов
    0.24
     harbor
    0.24
     format
    0.24
    raise
    0.24
    Activations Density 0.130%

    No Known Activations