© 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. 45027
    Prev
    Next
    INDEX
    Explanations

    names or titles

    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
     alleg
    -0.08
    zan
    -0.07
    è¿Ļæĺ¯çĶ±äºİ
    -0.07
    çļĦç¾İ女
    -0.07
     fart
    -0.07
    èĢģå©Ĩ
    -0.06
     stuff
    -0.06
    æĪijè¦ģæĬķè¯ī
    -0.06
    èµŀ
    -0.06
     Bong
    -0.06
    POSITIVE LOGITS
     kona
    0.09
    eiro
    0.08
    åĶĩè§Ĵ
    0.08
    eira
    0.08
    羸
    0.08
    ä¿®ç½Ĺ
    0.08
    mara
    0.07
    ä¸īæĪ¿
    0.07
    åĨ°å±±
    0.07
    afia
    0.07
    Activations Density 0.009%

    No Known Activations