© 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. 26495
    Prev
    Next
    INDEX
    Explanations

    select options

    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
    SOLE
    -0.08
    ä¸įè¾¾
    -0.07
    ç«ĭ
    -0.07
    forth
    -0.07
    ÙĨØ´
    -0.07
     SES
    -0.07
    ä¸įä¼ij
    -0.06
    ç«ĭåľ¨
    -0.06
     ÄIJÃłm
    -0.06
    [...,
    -0.06
    POSITIVE LOGITS
    çĴĢ
    0.08
    avra
    0.07
    åħij
    0.07
    igi
    0.07
    entr
    0.07
    à¹ģà¸ŀร
    0.07
    æľīäººåľ¨
    0.07
    ÙģتÙĩ
    0.07
    ÑĨеп
    0.07
    ÙĦب
    0.07
    Activations Density 0.004%

    No Known Activations