© 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. 7162
    Prev
    Next
    INDEX
    Explanations

    parts of an object

    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
    èĥĮåIJİçļĦ
    -0.11
    èĥĮåIJİ
    -0.10
    çļĦèĥĮåIJİ
    -0.09
    amil
    -0.09
     frontline
    -0.08
    åĪĨå¸ĥåľ¨
    -0.08
    åŃĺåľ¨äºİ
    -0.08
    æĶ¾åľ¨
    -0.08
    ulty
    -0.07
    åĩºçİ°åľ¨
    -0.07
    POSITIVE LOGITS
    most
    0.12
    θεν
    0.09
    ward
    0.09
    -most
    0.09
    สุà¸Ķ
    0.08
    åĴĮåIJİ
    0.08
    /current
    0.08
    æĸ¹çļĦ
    0.08
    wards
    0.07
    éĥ¨çļĦ
    0.07
    Activations Density 0.123%

    No Known Activations