© 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. 8586
    Prev
    Next
    INDEX
    Explanations

    different rates or fixed separation

    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
    ë°ľ
    -0.07
    æĭľ
    -0.07
    stit
    -0.07
    礼
    -0.07
    è·
    -0.06
    egi
    -0.06
    å¨ģ
    -0.06
    å½ĵãģŁ
    -0.06
    äºĭ
    -0.06
    ilu
    -0.06
    POSITIVE LOGITS
    ä¸Ģèĩ´æĢ§
    0.09
    约æĿŁ
    0.08
    ä¿ĿæĮģä¸Ģèĩ´
    0.08
     consistency
    0.08
    çļĦä¸Ģèĩ´æĢ§
    0.08
    çļĦè¦ģæ±Ĥ
    0.08
    强åĪ¶æī§è¡Į
    0.08
    ä¹ŁåıĹåĪ°
    0.08
    为äºĨ满足
    0.08
    νÏİ
    0.08
    Activations Density 0.002%

    No Known Activations