© 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. 2996
    Prev
    Next
    INDEX
    Explanations

    the same

    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
    æľīåħ¶ä»ĸ
    -0.08
    åı¯æĺ¯
    -0.07
    ÑĢее
    -0.07
    没æľī
    -0.07
    åı¯æĺ¯åľ¨
    -0.07
    æľīçļĦæĺ¯
    -0.07
    ×ĺ×Ļ×Ŀ
    -0.07
    æľīæĦıä¹ī
    -0.07
    uggle
    -0.07
     rien
    -0.07
    POSITIVE LOGITS
     same
    0.14
    same
    0.11
     mismo
    0.10
     necessary
    0.10
     mêmes
    0.09
     misma
    0.09
     SAME
    0.09
     greatest
    0.09
     mesma
    0.09
    ä¸Ģç§į
    0.08
    Activations Density 0.806%

    No Known Activations