© 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. 37451
    Prev
    Next
    INDEX
    Explanations

    mathematics and science terms

    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
    Negative Logits
    éĻ¢æīĢ
    -0.09
    awatan
    -0.08
    ä¸Ģå¤ķ
    -0.08
    umbing
    -0.08
    ÙĪعة
    -0.08
    _orientation
    -0.08
    éné
    -0.08
    æĥħåĨµåIJİ
    -0.08
    rette
    -0.08
    ereum
    -0.08
    POSITIVE LOGITS
    æ¦Ĥ念
    0.09
    çļĦæ¦Ĥ念
    0.09
    æ¦Ĥ念çļĦ
    0.08
    çļĦå®ļä¹ī
    0.08
    çļĦåŁºæľ¬
    0.08
    _
    0.08
    åŁºæľ¬æ¦Ĥ念
    0.06
    andar
    0.06
    æĺ¯æĮĩ
    0.06
    å®ļä¹ī
    0.06
    Activations Density 0.001%

    No Known Activations