© 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. 27788
    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
    alc
    -0.07
    è°ĥ
    -0.06
    è¿ŀåIJĮ
    -0.06
    調
    -0.06
    ola
    -0.06
    å¦Ĥ约
    -0.06
    ropa
    -0.06
    U
    -0.06
    TM
    -0.06
    b
    -0.05
    POSITIVE LOGITS
     /*#__
    0.09
     *__
    0.09
    flater
    0.08
     YYS
    0.08
    _marshall
    0.08
    amble
    0.08
    æŁ¥çľĭåħ¨æĸĩ
    0.08
    ÙĪاÙħ
    0.08
    ç»´çĶŁç´łåĴĮ
    0.07
    sembl
    0.07
    Activations Density 0.002%

    No Known Activations