© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60847
    Prev
    Next
    INDEX
    Explanations

    change or variation

    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
    جاÙĩ
    -0.08
    é¾Ļæ±Ł
    -0.07
    æĪĸèĢħ说
    -0.07
    çļĦ大éĥ¨åĪĨ
    -0.07
    ucker
    -0.07
     riêng
    -0.07
     seperate
    -0.07
     sekaligus
    -0.07
    æĺ¯æĢİä¹Ī
    -0.07
    echa
    -0.06
    POSITIVE LOGITS
     depending
    0.09
    ä½Ĩèĩ³å°ij
    0.09
     slight
    0.08
     dependendo
    0.08
    depending
    0.08
     variations
    0.08
    éļ¾åħį
    0.07
    ç¨įæľī
    0.07
    åıĸåĨ³äºİ
    0.07
    EndPoint
    0.07
    Activations Density 0.076%

    No Known Activations