© 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. 27912
    Prev
    Next
    INDEX
    Explanations

    utility or mode

    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
    asc
    -0.07
    ç½ijç«Ļ导èĪª
    -0.06
    oler
    -0.06
    orit
    -0.06
    飬
    -0.06
    strup
    -0.06
    ลาม
    -0.06
    ational
    -0.06
    èĢIJ
    -0.06
    aju
    -0.06
    POSITIVE LOGITS
    %X
    0.09
    æłı
    0.08
     elective
    0.08
    ÐłÐIJÐĹ
    0.08
    æľºåĪ¶
    0.08
    жеÑĤ
    0.08
    gerecht
    0.08
    åĻ¨
    0.07
    设置
    0.07
    è®¾ç½®åľ¨
    0.07
    Activations Density 0.378%

    No Known Activations