© 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. 40932
    Prev
    Next
    INDEX
    Explanations

    end stage renal

    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
    пли
    -0.09
    æľºçģµ
    -0.08
    viron
    -0.08
    ä¸ºåŁºç¡ĢçļĦ
    -0.07
    FromArray
    -0.07
    èµ·æĿ¥åIJ§
    -0.07
    æľĪå¼Ģå§ĭ
    -0.07
    uki
    -0.07
    orme
    -0.07
    Äĥm
    -0.07
    POSITIVE LOGITS
    /end
    0.14
    =end
    0.13
    ç»Ī
    0.12
    çµĤ
    0.12
    ãĤĴè¿İ
    0.12
    Reached
    0.11
     конÑĨов
    0.11
     reached
    0.10
     Akhir
    0.10
    å½Ĵ宿
    0.10
    Activations Density 0.109%

    No Known Activations