© 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. 16631
    Prev
    Next
    INDEX
    Explanations

    deflated condition, keeping, reduced, inactive

    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
    ÑħÑĢа
    -0.08
    antro
    -0.08
    adah
    -0.08
    ä¸įæľ½
    -0.07
     quicker
    -0.07
     nowadays
    -0.07
    çļĭ
    -0.07
    oir
    -0.07
    ()[
    -0.07
    æ°¸ä¸į
    -0.07
    POSITIVE LOGITS
    ä½ĨéļıçĿĢ
    0.11
    éĤ£æŶåĢĻ
    0.09
    èĢĮçİ°åľ¨
    0.09
    _until
    0.08
    å¤Ħäºİ
    0.08
    à¸Ńยูà¹Ī
    0.08
    èĢĮå¦Ĥä»Ĭ
    0.08
    utow
    0.08
    èĻķæĸ¼
    0.08
    çĬ¶æĢģä¸ĭ
    0.08
    Activations Density 0.218%

    No Known Activations