© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44194
    Prev
    Next
    INDEX
    Explanations

    stereochemistry, stereoisomerism, stereoselective

    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
    stig
    -0.08
    ÙĨÛĮÙĨ
    -0.08
    soever
    -0.08
    schede
    -0.08
    enaire
    -0.08
    yar
    -0.08
    ments
    -0.08
    æ·ĭæ¼ĵ
    -0.08
    stät
    -0.07
    ertest
    -0.07
    POSITIVE LOGITS
    opsis
    0.09
    abble
    0.08
    ally
    0.07
    uous
    0.07
    pher
    0.07
    agogue
    0.07
    icto
    0.07
    andex
    0.07
    ore
    0.07
    kees
    0.07
    Activations Density 0.010%

    No Known Activations