© 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. 21136
    Prev
    Next
    INDEX
    Explanations

    causal conjunctions

    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
    mot
    -0.08
    νÏĮ
    -0.07
     indeed
    -0.07
    Mot
    -0.07
     ArgumentNullException
    -0.06
    åĸĿä¸ĢæĿ¯
    -0.06
    ãģıãĤĮãģŁ
    -0.06
    ä¹Łæľª
    -0.06
     volta
    -0.06
    .nr
    -0.06
    POSITIVE LOGITS
    æĪij说
    0.08
    æĪijæĺ¯åľ¨
    0.07
    ×ķ×ļ
    0.07
    Äĩi
    0.07
    еÑĩÑĮ
    0.07
    estad
    0.07
    EMAIL
    0.07
    bers
    0.07
    egas
    0.06
    ishing
    0.06
    Activations Density 0.020%

    No Known Activations