© 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. 11417
    Prev
    Next
    INDEX
    Explanations

    Möbius transformation

    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
    iller
    -0.07
    رسÛĮ
    -0.07
    illé
    -0.07
    -Clause
    -0.07
    deka
    -0.07
    çĴŀ
    -0.07
    ikai
    -0.07
    (","
    -0.07
    æĸ°å±Ģ
    -0.07
    HOST
    -0.06
    POSITIVE LOGITS
    æĺ¥æ¸¸
    0.08
    andr
    0.07
     instrucc
    0.07
    ÚĨÙĩ
    0.07
    éĢ£éİĸ
    0.07
    uera
    0.07
    cken
    0.06
    ocr
    0.06
     exercitation
    0.06
    ارد
    0.06
    Activations Density 0.001%

    No Known Activations