© 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. 11802
    Prev
    Next
    INDEX
    Explanations

    SQL and programming files

    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
    )$/
    -0.08
    ä¹ĭ称çļĦ
    -0.08
     olmayan
    -0.07
    ãĢįãĢģãĢĮ
    -0.07
    "/
    -0.07
     ÙħختÙĦÙģÛĮ
    -0.07
     })(
    -0.07
    ãĢģãĢģ
    -0.07
    </
    -0.07
    **”
    -0.07
    POSITIVE LOGITS
    áŁĶ
    0.07
    ï½ŀãĢĤ
    0.07
    %E
    0.07
    áģĭ
    0.07
     '');
    0.07
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    æīĩ
    0.06
    ãĢĤ
    0.06
     ÙĪØ°ÙĦÙĥ
    0.06
    \\.
    0.06
    Activations Density 0.231%

    No Known Activations