© 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. 13476
    Prev
    Next
    INDEX
    Explanations

    separate or unified structures

    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
     Independ
    -0.10
     independently
    -0.09
    ç«ĭä¿¡
    -0.07
    çıĬ
    -0.07
    assy
    -0.07
     Poli
    -0.07
    åĽ½ä¹ĭ
    -0.07
    TTY
    -0.07
    æľīæį®
    -0.07
    Independ
    -0.07
    POSITIVE LOGITS
    绣ä¸ĢçļĦ
    0.16
    绣ä¸Ģ
    0.16
     unified
    0.16
     еди
    0.15
    åIJĪ并
    0.15
    ä¸įåĪĨ
    0.14
    åįķä¸Ģ
    0.14
    åľ¨ä¸Ģèµ·çļĦ
    0.14
     unify
    0.14
    ä¸Ģä½ĵåĮĸ
    0.13
    Activations Density 0.220%

    No Known Activations