© 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. 15332
    Prev
    Next
    INDEX
    Explanations

    well differentiated

    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¸įèµ·æĿ¥
    -0.07
    łí
    -0.06
    agon
    -0.06
    èı
    -0.06
    ัà¸Ļà¸Ĺ
    -0.06
    AGR
    -0.06
    prus
    -0.06
     nad
    -0.06
    å¿ĥæĤ¸
    -0.06
     thr
    -0.06
    POSITIVE LOGITS
    ukul
    0.08
    zell
    0.07
    iol
    0.07
    eringen
    0.07
    ApplicationContext
    0.07
    onom
    0.07
    cking
    0.07
    Ø®ÙĨ
    0.07
    æss
    0.07
    ´Ģ
    0.07
    Activations Density 0.018%

    No Known Activations