© 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. 9764
    Prev
    Next
    INDEX
    Explanations

    millions of finishers

    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
    ité
    -0.07
    è·»
    -0.07
    éĻħ
    -0.07
    bbie
    -0.07
     Stevenson
    -0.07
    stät
    -0.07
     Monte
    -0.06
    oloc
    -0.06
    elli
    -0.06
    彬彬
    -0.06
    POSITIVE LOGITS
    EventListener
    0.07
    uhl
    0.07
    ụng
    0.07
    æīĭæľºç«Ļ
    0.07
    çIJ³å¨ľ
    0.07
    å¤ĦçIJĨæĸ¹å¼ı
    0.07
    <!--[
    0.07
     prega
    0.07
     lidi
    0.07
    =>"
    0.07
    Activations Density 0.006%

    No Known Activations