© 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. 23355
    Prev
    Next
    INDEX
    Explanations

    majority

    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
    оÑģÑĮ
    -0.10
    æł·çļĦ
    -0.10
    åħ¢åħ¢ä¸ļä¸ļ
    -0.10
    jom
    -0.10
    俱ä¹IJéĥ¨
    -0.10
    ÑģÑı
    -0.09
    身临åħ¶å¢ĥ
    -0.09
    缸è¾ħ缸æĪIJ
    -0.09
    ä¼ĹæīĢåij¨çŁ¥
    -0.09
    heden
    -0.09
    POSITIVE LOGITS
    ÙĬ
    0.08
    ing
    0.08
     (>
    0.07
    æĥħåĨµä¸ĭ
    0.07
    ed
    0.07
     of
    0.06
    æĦıè§ģ
    0.06
    ei
    0.06
    ink
    0.06
    y
    0.06
    Activations Density 0.023%

    No Known Activations