© 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. 20637
    Prev
    Next
    INDEX
    Explanations

    version, edition, clinics, career

    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
    æĹ¢æĺ¯
    -0.08
    ħ
    -0.07
     sia
    -0.07
     both
    -0.07
    æ¯Ķåħ¶ä»ĸ
    -0.07
    ä½ĻçĶŁ
    -0.07
     vừa
    -0.07
    ynet
    -0.07
    æĺİæĺİæĺ¯
    -0.06
    ä»ĸ们éĥ½æĺ¯
    -0.06
    POSITIVE LOGITS
     counterparts
    0.08
    åIJĴ
    0.08
    ä¾Ŀä¾Ŀ
    0.08
    大åIJį
    0.08
     lẫn
    0.08
    utul
    0.07
    åĴĮåķĨä¸ļ
    0.07
    ffre
    0.07
    ¾¸
    0.07
    apura
    0.07
    Activations Density 0.291%

    No Known Activations