© 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. 23648
    Prev
    Next
    INDEX
    Explanations

    configuration and components

    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
    èĢĮä¸įæĺ¯
    -0.08
    æľīè¿Ļæł·çļĦ
    -0.08
    èĢĮéĿŀ
    -0.07
     infatti
    -0.07
    ê·¼
    -0.07
    uhn
    -0.07
     Lars
    -0.06
    Äģt
    -0.06
    Äģd
    -0.06
     totiž
    -0.06
    POSITIVE LOGITS
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.11
    çŃīåħ¶ä»ĸ
    0.11
     thereafter
    0.10
     altrettanto
    0.08
    èĭ¥å¹²
    0.08
    éĥ¨åĪĨç»ĦæĪIJ
    0.07
     afterwards
    0.07
    大æŀĹ
    0.07
     ÑģобÑģÑĤвенно
    0.07
     afterward
    0.07
    Activations Density 0.053%

    No Known Activations