© 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. 15823
    Prev
    Next
    INDEX
    Explanations

    places and concepts

    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
    Ŀ¼
    -0.09
    WithTitle
    -0.08
    WithContext
    -0.07
    .desc
    -0.07
    gota
    -0.07
    æĿ¯éħĴ
    -0.07
    æģ¶æĦı
    -0.07
     unnamed
    -0.07
    åĨĴçĿĢ
    -0.07
    _already
    -0.07
    POSITIVE LOGITS
    æ¯Ķåħ¶ä»ĸ
    0.11
    æ¯ĶæĻ®éĢļ
    0.10
    æĺ¯ä¸ĢéŨ
    0.10
     unlike
    0.10
     unique
    0.09
     inherently
    0.09
    çī¹æľī
    0.09
    çī¹æľīçļĦ
    0.09
    çĭ¬çī¹
    0.09
    ä¸įåIJĮäºİ
    0.09
    Activations Density 0.973%

    No Known Activations