© 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. 46304
    Prev
    Next
    INDEX
    Explanations

    month, Year, 2

    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
    aray
    -0.09
    igham
    -0.08
    ikota
    -0.08
    emouth
    -0.08
    abbr
    -0.08
    管çIJĨå±Ģ
    -0.08
    注éĶĢå¤ĩæ¡Ī
    -0.07
    ream
    -0.07
    pum
    -0.07
    ãĥ³ãĤ¹
    -0.07
    POSITIVE LOGITS
    ocio
    0.07
    åģļ个
    0.07
    je
    0.06
     W
    0.06
    为éĿŀ
    0.06
    holz
    0.06
    æĮģ
    0.06
    åĴĮçİĭ
    0.06
     ÙĪاÙĦÙħست
    0.06
     ed
    0.06
    Activations Density 0.006%

    No Known Activations