© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59796
    Prev
    Next
    INDEX
    Explanations

    book or types

    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
    Negative Logits
    t
    -0.07
    mon
    -0.06
    大
    -0.06
    ä¸Ģ
    -0.06
    åĪĨ
    -0.06
    åIJĮä¸Ĭ
    -0.06
    First
    -0.06
    稻
    -0.06
    s
    -0.06
    met
    -0.06
    POSITIVE LOGITS
    etheless
    0.10
    çļĦ人è¿ĺ
    0.08
    è¿Ŀåıįä¸Ĭè¿°
    0.08
    çĶ±æѤåı¯è§ģ
    0.08
    mium
    0.08
    ÐijÐļ
    0.08
    éĶĻè¿ĩçļĦ
    0.08
    away
    0.08
    æīĢæľīè¿ĻäºĽ
    0.08
    éĢļè¿ĩ以ä¸Ĭ
    0.08
    Activations Density 0.002%

    No Known Activations