© 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. 45625
    Prev
    Next
    INDEX
    Explanations

    mirrors, polynomials, light, rate, entry, rows

    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
    áĥķáĥĺ
    -0.06
    롯
    -0.06
    lade
    -0.06
    éħµ
    -0.06
    ł
    -0.06
    åѦçĶŁä»£è¡¨
    -0.06
    ä¸Ń西åĮ»
    -0.06
     contr
    -0.06
    åħ±æµİ
    -0.06
     cf
    -0.06
    POSITIVE LOGITS
    ợ
    0.08
    [,]
    0.08
    èĢĮå¾ĹåIJį
    0.07
    Å¡
    0.07
    çļĦæľīåħ³è§Ħå®ļ
    0.07
     [=
    0.07
    понен
    0.07
    Å¡ov
    0.07
    大夫
    0.07
     (âĢ¦)
    0.07
    Activations Density 0.012%

    No Known Activations