© 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. 59852
    Prev
    Next
    INDEX
    Explanations

    direction and orientation

    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
    æĢ»æķ°
    -0.07
    aporte
    -0.07
    amt
    -0.07
    è¿ĩ好
    -0.07
    isNaN
    -0.07
    ؤÙĪÙĦ
    -0.07
    容éĩı
    -0.07
    ::-
    -0.07
    :number
    -0.07
    волÑĮ
    -0.06
    POSITIVE LOGITS
     direction
    0.12
    æĸ¹åIJij
    0.11
    direction
    0.11
     напÑĢавление
    0.10
    æĸ¹åIJijçļĦ
    0.10
    Direction
    0.10
    à¸Ĺิศà¸Ĺาà¸ĩ
    0.10
    çļĦæĸ¹åIJij
    0.09
     Direction
    0.09
    æĸ¹åIJijåĴĮ
    0.09
    Activations Density 0.003%

    No Known Activations