© 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. 37830
    Prev
    Next
    INDEX
    Explanations

    award nominations

    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
    åĭĭ
    -0.06
    дово
    -0.06
    æĶ¿ç»©
    -0.06
    PackageName
    -0.06
    è´¯
    -0.06
    åħĨ
    -0.06
    主æµģçļĦ
    -0.05
    jeg
    -0.05
    讳
    -0.05
    halb
    -0.05
    POSITIVE LOGITS
    nowrap
    0.08
    zan
    0.08
    åıĪä¸Ģ个
    0.07
    edom
    0.07
    人äºĭ
    0.07
    微信æī«ä¸Ģæī«
    0.07
    won
    0.07
    обе
    0.07
    æİ¥è¿ij尾声
    0.07
    æīĢæľª
    0.07
    Activations Density 0.041%

    No Known Activations