© 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. 31994
    Prev
    Next
    INDEX
    Explanations

    navigating pages and configurations

    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
     DBNull
    -0.09
    UPI
    -0.09
    chet
    -0.08
    _ENDIAN
    -0.08
     razie
    -0.07
    entifier
    -0.07
    éĢĢä¿Ŀ
    -0.07
    ebel
    -0.07
    cka
    -0.07
    iteDatabase
    -0.07
    POSITIVE LOGITS
    (...)
    0.08
    \_
    0.08
    (...
    0.07
    è¿Ļ个éĹ®é¢ĺçļĦ
    0.06
    ↵↵    ↵
    0.06
    \<
    0.06
    ä¸Ģè¯į
    0.06
     Bra
    0.06
    ä½łæĺ¯ä¸Ģ个
    0.06
    ä½łæĺ¯ä¸ª
    0.06
    Activations Density 0.758%

    No Known Activations