© 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. 23543
    Prev
    Next
    INDEX
    Explanations

    numbers after 6

    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
    ë¡Ŀ
    -0.08
     helst
    -0.07
    holds
    -0.07
    orza
    -0.07
    rips
    -0.07
    byt
    -0.06
    bergen
    -0.06
    olk
    -0.06
    æĢ§åľ°
    -0.06
    ä¸įæĺİçļĦ
    -0.06
    POSITIVE LOGITS
    ষà§įà¦ł
    0.12
    teenth
    0.09
    oucher
    0.08
    ãģ¤ãģ®
    0.08
    หลวà¸ĩ
    0.08
    деÑģÑıÑĤ
    0.08
    tingham
    0.08
    chet
    0.08
    teborg
    0.08
    à¹Ĩ
    0.08
    Activations Density 0.361%

    No Known Activations