© 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. 52144
    Prev
    Next
    INDEX
    Explanations

    measure or map

    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
    abr
    -0.08
    obe
    -0.07
    éĹº
    -0.07
     Khai
    -0.07
    çĭ¸
    -0.07
    "@
    -0.07
    èĩ¨æĻĤ
    -0.07
    åĪĽæĸ°ä¸Ńå¿ĥ
    -0.07
    课é¢ĺç»Ħ
    -0.07
    æĶĺ
    -0.07
    POSITIVE LOGITS
    æ¼ı
    0.08
    opers
    0.07
    ordon
    0.07
    idane
    0.07
    ncer
    0.07
    æĺ¯ä¸Ģç§į
    0.06
    äne
    0.06
    arness
    0.06
     кÑĢа
    0.06
    eldes
    0.06
    Activations Density 0.019%

    No Known Activations