© 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. 51396
    Prev
    Next
    INDEX
    Explanations

    RFC or standard numbers

    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
    گر
    -0.07
    itch
    -0.06
    æĴĩ
    -0.06
    å¤į
    -0.06
     borderTop
    -0.06
    gang
    -0.06
    deo
    -0.06
    ä¹į
    -0.06
    isse
    -0.06
    nish
    -0.06
    POSITIVE LOGITS
    çļĦæľīåħ³è§Ħå®ļ
    0.09
    çļĦè°ĥæŁ¥
    0.08
    loud
    0.07
    inari
    0.07
    ë§ĮìĿ´
    0.07
    çļĦæľĢæĸ°
    0.07
    æķ¬ä¸ļç²¾ç¥ŀ
    0.07
    åı¥è¯Ŀ说
    0.07
     standpoint
    0.07
    ä½ľåĪĻ
    0.07
    Activations Density 0.164%

    No Known Activations