© 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. 23446
    Prev
    Next
    INDEX
    Explanations

    gear-equipped

    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
    meli
    -0.09
    ãģ¾ãģĽãĤĵãģĮ
    -0.08
    æıIJä¾ĽæĽ´å¤ļçļĦ
    -0.08
    esson
    -0.08
    iago
    -0.08
    melidir
    -0.08
    óc
    -0.08
    ôt
    -0.08
    æıIJä¾ĽæĽ´å¥½çļĦ
    -0.08
    ãģ§ãģĻãģĹ
    -0.08
    POSITIVE LOGITS
    çļĦä¸Ģç§į
    0.14
    çļĦä¸Ģ種
    0.11
    çļĦä¸Ģç§įæĸ¹å¼ı
    0.11
    äºİä¸Ģä½ĵçļĦ
    0.09
    ä»İèĢĮ
    0.09
    èĢĮæĪIJçļĦ
    0.09
    çļĦä¸Ģç±»
    0.09
    çļĦè¿ĩç¨ĭ
    0.09
    èĢĮå¾ĹåIJį
    0.08
    çļĦæŶåĢĻäºĨ
    0.08
    Activations Density 0.049%

    No Known Activations