© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57706
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¼ł
    -0.08
    åįĥ亿
    -0.07
    åįĥ家
    -0.06
    æįį
    -0.06
     Bor
    -0.06
    ãģ»ãģĨ
    -0.06
    /about
    -0.06
    模
    -0.06
     Tac
    -0.06
    _assign
    -0.06
    POSITIVE LOGITS
    kal
    0.08
    óle
    0.07
    ingers
    0.07
    Õ¥Õ¿
    0.07
    件ä¸Ń
    0.07
    ife
    0.07
    è¿ŀçĿĢ
    0.07
    个好
    0.07
    odik
    0.07
    elled
    0.07
    Activations Density 0.006%

    No Known Activations