© 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. 27757
    Prev
    Next
    INDEX
    Explanations

    numbers following 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
    ingin
    -0.08
     ÙħØ«
    -0.07
    ATAB
    -0.07
    utan
    -0.07
    >:</
    -0.07
    ersh
    -0.07
    ronics
    -0.07
    ddit
    -0.07
    ringe
    -0.06
    åĬŀæ³ķ
    -0.06
    POSITIVE LOGITS
     ryt
    0.07
    erman
    0.07
    iever
    0.07
     Pike
    0.06
     Covered
    0.06
    æ²Ĵäºĭ
    0.06
    æĻ¯è§Ĥ设计
    0.06
    åı¯ä»¥çIJĨ解
    0.06
    praw
    0.06
    ç¿»äºĨ
    0.06
    Activations Density 0.004%

    No Known Activations