© 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. 7790
    Prev
    Next
    INDEX
    Explanations

    variable names with underscores

    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
    ä¹ĭèī²
    -0.07
    ergestellt
    -0.07
    çļĦæĦıæĢĿ
    -0.07
    å®Įä¹ĭåIJİ
    -0.07
    Ùĭ
    -0.07
    Ø©
    -0.07
    igo
    -0.07
    ä¹ĭ大
    -0.07
    çļĦæŶåĢĻè¦ģ
    -0.07
    еÑĩ
    -0.06
    POSITIVE LOGITS
    çļĦ
    0.17
    ÛĮ
    0.13
    를
    0.12
    nya
    0.11
    ãĤĭ
    0.11
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.10
    çļĦãģª
    0.10
    ãĤĭãģĭ
    0.10
    à§ĩর
    0.10
    ìĿĦ
    0.09
    Activations Density 0.354%

    No Known Activations