© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20290
    Prev
    Next
    INDEX
    Explanations

    arrows, sights, stream, dimensions, signs

    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
    truc
    -0.08
    å°Ķé¡¿
    -0.08
    æīĢæľīè¿ĻäºĽ
    -0.07
    ley
    -0.07
    iam
    -0.07
    éĿĵ
    -0.07
    ãģī
    -0.07
     Edels
    -0.06
    ilden
    -0.06
    è¿Ļ个æķ°åŃĹ
    -0.06
    POSITIVE LOGITS
    åĪĨåĪ«æĺ¯
    0.13
    åIJĦèĩªçļĦ
    0.11
    åĪĨåĪ«ä¸º
    0.11
    ä¹ĭä¸ĢçļĦ
    0.11
    é½IJåħ¨
    0.11
    çī¹åĪ«æĺ¯
    0.11
    åIJĦèĩª
    0.10
    é½IJåħ¨çļĦ
    0.10
     respectively
    0.10
    æıĥ
    0.10
    Activations Density 0.171%

    No Known Activations