© 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. 62327
    Prev
    Next
    INDEX
    Explanations

    opportunity

    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
    ientes
    -0.07
    estand
    -0.07
    éĤ£åı¯æĺ¯
    -0.07
    æłij人
    -0.07
    èµ
    -0.07
    å¦Ħ
    -0.07
    å°Ķçī¹
    -0.07
    ä¼¼
    -0.06
    iente
    -0.06
     bilin
    -0.06
    POSITIVE LOGITS
    æŀľçĦ¶
    0.23
     indeed
    0.19
    æŀľçľŁ
    0.17
    ä¹Łç¡®å®ŀ
    0.17
     effectivement
    0.17
    ç¡®å®ŀ
    0.17
    ç¡®å®ŀæĺ¯
    0.16
    æŀľçĦ¶æĺ¯
    0.15
    ç¡®æľī
    0.15
    çļĦç¡®
    0.14
    Activations Density 0.552%

    No Known Activations