© 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. 31552
    Prev
    Next
    INDEX
    Explanations

    derived sequences or names

    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
    æĭ¥
    -0.08
     hinweg
    -0.07
    /bl
    -0.07
    åĪ°ä½İ
    -0.07
    Occurred
    -0.07
    /all
    -0.07
    天çļĦ
    -0.07
    ullet
    -0.07
    /o
    -0.07
    /tree
    -0.07
    POSITIVE LOGITS
    åĴĮçī¹çĤ¹
    0.10
    åĴĮä½ľçĶ¨
    0.09
    åĴĮæĦıä¹ī
    0.09
    çī¹çĤ¹æĺ¯
    0.07
    arkan
    0.07
    ä¸į详
    0.07
    ibat
    0.07
    ä¸İä½ľçĶ¨
    0.07
    ikt
    0.07
    /activity
    0.06
    Activations Density 0.003%

    No Known Activations