© 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. 58624
    Prev
    Next
    INDEX
    Explanations

    spock.li, Hua, Tel, Bridges

    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
     âĵĺ
    -0.07
    波士
    -0.07
    -archive
    -0.07
    omas
    -0.07
    duit
    -0.07
    ebol
    -0.07
    æĢ»æĺ¯ä¼ļ
    -0.06
     armado
    -0.06
     вплоÑĤÑĮ
    -0.06
    -Bold
    -0.06
    POSITIVE LOGITS
    顾åIJįæĢĿä¹ī
    0.08
    åıĪ称
    0.08
    ä»Ģä¹ĪæĦıæĢĿ
    0.08
    ä¹Łå°±æĺ¯
    0.07
     czyli
    0.07
    ä¸ŃåĽ½å®¶
    0.07
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.07
    éĿ¢è®®
    0.07
    åıĪ称为
    0.07
    oup
    0.07
    Activations Density 0.319%

    No Known Activations