© 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. 15388
    Prev
    Next
    INDEX
    Explanations

    age range

    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
    اÙĨع
    -0.08
    ented
    -0.08
    æľīåħ³äºİ
    -0.07
    ÙĨع
    -0.07
    人æĦı
    -0.07
    atil
    -0.07
    åŃľ
    -0.07
    uddenly
    -0.07
    .Done
    -0.07
    é£İéĻ©åĪĨæŀIJ
    -0.07
    POSITIVE LOGITS
     varying
    0.07
     varied
    0.07
    (range
    0.07
    æľĢ大çļĦ
    0.07
     ranged
    0.07
    xcb
    0.07
    èĥ¡
    0.07
    åĬłæĸ¯
    0.06
    vary
    0.06
     ranging
    0.06
    Activations Density 0.184%

    No Known Activations