© 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. 24235
    Prev
    Next
    INDEX
    Explanations

    central carrier bright display

    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
    wesen
    -0.08
     NotImplemented
    -0.08
    åıĪä¸į
    -0.08
    翻天è¦Ĩ
    -0.07
    agenda
    -0.07
    enser
    -0.07
    çĥŃéŨæĸĩç«ł
    -0.07
    大ä¹ī
    -0.07
    è¾Ĺ转
    -0.07
    广
    -0.07
    POSITIVE LOGITS
     brightest
    0.07
    ä¿¡æģ¯ä¸Ńå¿ĥ
    0.07
    ä¸Ńå¿ĥåĴĮ
    0.07
    noc
    0.07
    为ä¸Ńå¿ĥ
    0.07
     полоÑģ
    0.07
    usel
    0.07
    为ä¸Ńå¿ĥçļĦ
    0.07
    çıĢ
    0.07
     nul
    0.07
    Activations Density 0.005%

    No Known Activations