© 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. 2142
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    mira
    -0.08
    isé
    -0.08
    enj
    -0.07
    hammer
    -0.07
    ä¸įå¦ĤæĦı
    -0.07
     Lavor
    -0.07
    à·Ģà·ı
    -0.07
    orny
    -0.07
    afx
    -0.07
    kst
    -0.07
    POSITIVE LOGITS
     arre
    0.06
    å¾Ĺè¿ĩ
    0.06
    nyder
    0.06
     presum
    0.06
     cầu
    0.06
    ìŀħ
    0.06
    è®¤çľŁå±¥è¡Į
    0.06
    0.06
     carry
    0.06
     ums
    0.06
    Activations Density 0.005%

    No Known Activations