© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39458
    Prev
    Next
    INDEX
    Explanations

    `shouldn’t have`

    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
    åŃĺåľ¨ä¸ĢäºĽ
    -0.08
    é¦ĸåħĪéľĢè¦ģ
    -0.07
    ä¹Łå¹¶éĿŀ
    -0.07
     impun
    -0.07
    Mocks
    -0.07
    istem
    -0.07
    iled
    -0.07
     HACK
    -0.07
    istre
    -0.07
     simultaneously
    -0.07
    POSITIVE LOGITS
     gotta
    0.08
    è¯ķè¯ķåIJ§
    0.08
     ÏĮμÏīÏĤ
    0.07
     gonna
    0.07
     кÑģÑĤаÑĤи
    0.07
     ведÑĮ
    0.07
    人å¤ļ
    0.07
    /Instruction
    0.07
    åĭ¿
    0.07
    пÑĢоÑĩем
    0.07
    Activations Density 0.954%

    No Known Activations