© 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. 10000
    Prev
    Next
    INDEX
    Explanations

    improving, exploring, planning, extending, deleting

    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
    ä¸įå·®
    -0.08
    æľĢå¿«çļĦéĢŁåº¦
    -0.07
    å¾Īå¤ļéĹ®é¢ĺ
    -0.07
    以赴
    -0.07
    viron
    -0.07
    anaan
    -0.07
    å½ĵåħ¶
    -0.06
    åIJijæĹ¥
    -0.06
    æĹłè®ºæĺ¯åľ¨
    -0.06
    AMENT
    -0.06
    POSITIVE LOGITS
    åĴĮä¿ĿæĬ¤
    0.11
    åĴĮæĶ¹åĸĦ
    0.11
    åĴĮç»´æĬ¤
    0.11
    åĴĮæıIJåįĩ
    0.11
    åĴĮä¼ĺåĮĸ
    0.10
    åĴĮåĪ©çĶ¨
    0.10
    åĴĮæıIJé«ĺ
    0.10
    åĴĮå¤ĦçIJĨ
    0.10
    åĴĮåĪĨæŀIJ
    0.10
    åĴĮçĽijçĿ£
    0.09
    Activations Density 0.014%

    No Known Activations