© 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. 47181
    Prev
    Next
    INDEX
    Explanations

    cortical circuits and nerves

    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
    ä¾ĭåŃIJ
    -0.08
    çĶ¨æĪ·æıIJä¾Ľ
    -0.07
    çļĦä¾ĭåŃIJ
    -0.07
    landet
    -0.06
    estens
    -0.06
    lå
    -0.06
    ä½ľåĪĻ
    -0.06
    ¬
    -0.06
     exemples
    -0.06
    rella
    -0.06
    POSITIVE LOGITS
    æ¯ıä¸Ģ个è§ĴèIJ½
    0.08
    -dominated
    0.08
    oral
    0.07
    veren
    0.07
    veli
    0.07
    æķ´ä½ĵçļĦ
    0.07
    cosa
    0.07
    çļĦæķ´ä½ĵ
    0.07
    ovin
    0.07
    ellig
    0.07
    Activations Density 0.044%

    No Known Activations