© 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. 44993
    Prev
    Next
    INDEX
    Explanations

    `smallest` `value` `in`

    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
    éļĶ
    -0.08
    —
    -0.07
    ä¸Ģå¼ı
    -0.07
    è¿ĩ客
    -0.07
    çľĭä¸į
    -0.07
    éĢļ
    -0.07
    æ»´
    -0.06
    _totals
    -0.06
    éļı
    -0.06
    çľĭå¾Ĺ
    -0.06
    POSITIVE LOGITS
    ytte
    0.10
    è¦ģæıIJé«ĺ
    0.09
     Ingr
    0.08
    èĮĥåĽ´åĨħ使çĶ¨
    0.08
    utilise
    0.08
    åIJĪçIJĨåĪ©çĶ¨
    0.08
    åľ°åĿĢä½įäºİ
    0.07
    ñez
    0.07
    人æĿ¥è¯´
    0.07
    åĨľæŀĹ
    0.07
    Activations Density 0.002%

    No Known Activations