© 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. 32912
    Prev
    Next
    INDEX
    Explanations

    ways questions are phrased

    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
    èĭ¥éĿŀ
    -0.07
    auc
    -0.07
    å¸ĮæľĽåĴĮ
    -0.06
    izzi
    -0.06
    ¬
    -0.06
    á»
    -0.06
    oe
    -0.06
    è¶Ĭ
    -0.06
    è¿ij
    -0.06
    ÑĢки
    -0.06
    POSITIVE LOGITS
    å¯¹ä½łè¯´
    0.08
    ä¸įèĭŁ
    0.07
    cern
    0.07
    åĸ§åĵĹ
    0.07
    è¿ĺåºĶå½ĵ
    0.07
    æī§è¡ĮæĥħåĨµ
    0.06
    beda
    0.06
    éĩįçļĦ
    0.06
    西åıĮçīĪ纳
    0.06
    /plain
    0.06
    Activations Density 0.068%

    No Known Activations