© 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. 2140
    Prev
    Next
    INDEX
    Explanations

    May you do

    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
    åı·çļĦ
    -0.08
    å¢Ł
    -0.08
    æĢİä¹ĪåĬŀåij¢
    -0.08
    ä½łè¿ĺåľ¨
    -0.07
    Ready
    -0.07
    echa
    -0.07
    åħ¨ç¨ĭ
    -0.07
    atih
    -0.07
    é¢ĩ为
    -0.07
    家æķĻ
    -0.07
    POSITIVE LOGITS
    æĹ©æĹ¥
    0.11
    ä¿Ŀä½ij
    0.08
     wszel
    0.08
    æīĢæĥ³
    0.08
    çļĦæĦ¿æľĽ
    0.07
    ä¹Łå¸ĮæľĽ
    0.07
    åģ¥åº·
    0.07
     legyen
    0.07
    çļĦç¥Ŀç¦ı
    0.07
    æĦ¿æľĽ
    0.07
    Activations Density 0.072%

    No Known Activations