© 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. 57511
    Prev
    Next
    INDEX
    Explanations

    public:

    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
    足
    -0.08
    ãĤĥ
    -0.08
    æ´Ľæĸ¯
    -0.07
    ÙĪØ·
    -0.07
    ushman
    -0.07
     tester
    -0.07
    à§ģর
    -0.07
    vento
    -0.07
    ritch
    -0.07
    çĭ©
    -0.07
    POSITIVE LOGITS
    æºIJæºIJ
    0.08
    ลà¸Ńย
    0.07
    åľ¨ä»Ĭ
    0.07
     سÙĬر
    0.06
    ä¾Ľ
    0.06
    Ń
    0.06
    端åĢª
    0.06
    éĢĴ
    0.06
    ä½łæĥ³è¦ģ
    0.06
     Touch
    0.06
    Activations Density 0.003%

    No Known Activations