© 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. 4626
    Prev
    Next
    INDEX
    Explanations

    rotating things and space concepts

    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
    ä¹ĭ家
    -0.08
    è·ĭ
    -0.08
     solide
    -0.08
    è©°ãĤģ
    -0.07
    umpl
    -0.07
     solid
    -0.07
     pire
    -0.07
    Ñĸм
    -0.07
    ä¸ĢçĤ¹ä¸Ģæ»´
    -0.07
    ÏĪη
    -0.07
    POSITIVE LOGITS
     deflect
    0.09
    纬
    0.08
     latitude
    0.07
    åľ°çIJĥ
    0.07
    Routing
    0.07
     ge
    0.07
     Rot
    0.07
     rued
    0.07
     strike
    0.07
     rotating
    0.07
    Activations Density 0.003%

    No Known Activations