© 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. 21471
    Prev
    Next
    INDEX
    Explanations

    groups and modules

    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
    ä¸īåľ°
    -0.07
    elus
    -0.06
    濯
    -0.06
    鹦é¹ī
    -0.06
    带åħ¥
    -0.06
    cha
    -0.06
    以为æĺ¯
    -0.06
    带äºĨ
    -0.06
    è·¨
    -0.06
    Block
    -0.06
    POSITIVE LOGITS
    æĢ»æķ°çļĦ
    0.08
    æķ°éĩı
    0.08
    çļĦæķ°éĩı
    0.08
    ç©·
    0.08
    æķ¸éĩı
    0.07
    erable
    0.07
    æķ°éĩıåĴĮ
    0.07
    æķ°éĩıçļĦ
    0.07
     repertoire
    0.07
    大大å°ıå°ıçļĦ
    0.07
    Activations Density 0.025%

    No Known Activations