© 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. 3211
    Prev
    Next
    INDEX
    Explanations

    and * a

    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
    æķĪçİĩåĴĮ
    -0.07
    ãĤıãĤĬ
    -0.07
    çĶļèĩ³åľ¨
    -0.07
    èĢĮä¸Ķåľ¨
    -0.07
    anoi
    -0.07
    交æµģä¸İ
    -0.07
    交æµģåĴĮ
    -0.07
     Vui
    -0.07
     strr
    -0.07
     neither
    -0.06
    POSITIVE LOGITS
    åĬłæĭ¿å¤§
    0.07
    ugno
    0.07
     another
    0.07
    itim
    0.07
    å¹´æŶéĹ´
    0.07
     اÛĮÙĨÚ©Ùĩ
    0.07
    amed
    0.07
     sebuah
    0.07
    -Smith
    0.06
    次
    0.06
    Activations Density 0.127%

    No Known Activations