© 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. 600
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols

    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
    gether
    -0.14
    Ø©
    -0.09
    ation
    -0.09
    à§įত
    -0.08
    Ñı
    -0.08
    اÙĭ
    -0.07
    ÙĦ
    -0.07
    áĥĿáĥij
    -0.07
    ever
    -0.06
    ìĦľ
    -0.06
    POSITIVE LOGITS
    ¹
    0.11
    enticator
    0.11
    sing
    0.11
    sst
    0.11
    sstr
    0.11
    azard
    0.10
    sense
    0.10
    klen
    0.10
    ħ
    0.10
    schen
    0.09
    Activations Density 0.008%

    No Known Activations