© 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. 47256
    Prev
    Next
    INDEX
    Explanations

    including terms or categories

    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
    elos
    -0.08
    OrElse
    -0.07
    —or
    -0.07
    åīį款
    -0.07
    yet
    -0.07
    åıĪæĪĸèĢħ
    -0.07
    ký
    -0.07
     dennoch
    -0.06
    OfClass
    -0.06
    áĥĺáĥIJ
    -0.06
    POSITIVE LOGITS
    åľ¨åĨħçļĦ
    0.20
    åľ¨åĨħ
    0.16
    ä¹ŁåĮħæĭ¬
    0.14
    ä½Ĩä¸įéĻIJäºİ
    0.13
     didalamnya
    0.10
     lẫn
    0.10
    è¿ĺåĮħæĭ¬
    0.09
    ä½Ĩ以
    0.09
    åľ¨éĩĮéĿ¢
    0.09
    ä¸įéĻIJäºİ
    0.08
    Activations Density 0.409%

    No Known Activations