© 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. 61171
    Prev
    Next
    INDEX
    Explanations

    strain names and classifications

    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
    ajs
    -0.08
    æķ£
    -0.07
    她æĥ³
    -0.07
    ä¸Ģè¦ģ
    -0.06
    åıĸåĨ³
    -0.06
    å®ŀç¼´
    -0.06
     Trot
    -0.06
    è¿Ļç§įäºĭ
    -0.06
    طب
    -0.06
     applicable
    -0.06
    POSITIVE LOGITS
    ä¸Ģåı·
    0.09
     prec
    0.08
    ersey
    0.07
    äºĮåı·
    0.07
    ç¼ĸåı·
    0.07
     reportedly
    0.07
     заблÑĥ
    0.07
    æīĢå±ķ示
    0.07
    æĿijæĿij
    0.07
    ä¸īåı·
    0.07
    Activations Density 0.295%

    No Known Activations