© 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. 62053
    Prev
    Next
    INDEX
    Explanations

    much greater effect

    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
    ä¸įæĸŃæݢ索
    -0.09
    è¿Ľä¸ĢæŃ¥æ·±åĮĸ
    -0.08
    ä¸įæĸŃæ·±åĮĸ
    -0.08
    è¿Ľä¸ĢæŃ¥åıijå±ķ
    -0.08
     íĬ¹ìłķ
    -0.07
    深深çļĦ
    -0.07
    lima
    -0.07
    autaire
    -0.07
    ness
    -0.07
    å¹´åįİ
    -0.07
    POSITIVE LOGITS
    ä¹İåħ¶
    0.09
    ively
    0.09
    ingly
    0.09
    ÃŃss
    0.07
    èĤª
    0.07
    åĢįçļĦ
    0.07
    erable
    0.07
    /ext
    0.07
    ially
    0.07
    jub
    0.07
    Activations Density 0.075%

    No Known Activations