© 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. 7644
    Prev
    Next
    INDEX
    Explanations

    (R,S) stereoisomers

    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
    ä¸ĢæĿ¥
    -0.07
    åı¯æľī
    -0.07
    iebe
    -0.06
    å¾ĢæľŁç²¾å½©
    -0.06
    åįĬåĬŁ
    -0.06
    nTo
    -0.06
    ç½Ĺæ¹ĸ
    -0.06
    ennie
    -0.06
    inhas
    -0.06
    æĸŃ
    -0.06
    POSITIVE LOGITS
    /-
    0.08
    ï¸İ
    0.08
    åħ¼
    0.07
    emento
    0.07
    浦åĮº
    0.07
    opsis
    0.07
    æ¡ĤåĨł
    0.07
    вил
    0.06
    -ish
    0.06
    çīĪæľ¬çļĦ
    0.06
    Activations Density 0.014%

    No Known Activations