© 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. 57804
    Prev
    Next
    INDEX
    Explanations

    numbers, units, and scientific notation

    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
    zah
    -0.07
    rezz
    -0.06
    uell
    -0.06
    æĢĿæĥ³ä¸Ĭ
    -0.06
    æľ¯
    -0.06
    å°ıæĹ¶å·¦åı³
    -0.06
    мо
    -0.06
     Rodrig
    -0.06
    èĹ
    -0.06
    æĿ¥çļĦæŶåĢĻ
    -0.06
    POSITIVE LOGITS
    _macros
    0.08
    pto
    0.08
    reak
    0.07
    aci
    0.07
    伯çī¹
    0.07
    otka
    0.07
    anity
    0.07
    æĢ»åı°
    0.07
    èħ¦
    0.07
    ilos
    0.07
    Activations Density 0.001%

    No Known Activations