© 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. 33928
    Prev
    Next
    INDEX
    Explanations

    applications, fields, areas, sectors

    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
    رت
    -0.07
    æĽ²å¼ł
    -0.07
    èĩ³ä¸Ĭ
    -0.07
    绿水éĿĴå±±
    -0.07
    æĽ¾çĶ¨åIJį
    -0.06
    upas
    -0.06
    اج
    -0.06
    ä¹Łå¥½
    -0.06
    ä¸ĸä¸Ĭ
    -0.06
    å¾Ģå¾Ģ
    -0.06
    POSITIVE LOGITS
    大åŀĭ
    0.09
    inato
    0.08
     Ras
    0.08
     recién
    0.07
    æľĢæĸ°æĽ´æĸ°
    0.07
    ondre
    0.07
    ä¿ĿéĻ©
    0.07
    _hint
    0.07
    çļĦäºĭäºĨ
    0.07
    å°ıåŀĭ
    0.07
    Activations Density 0.225%

    No Known Activations