© 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. 55228
    Prev
    Next
    INDEX
    Explanations

    inside or within

    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
    çĶŁåľ¨
    -0.07
    avent
    -0.07
    èĬ±åľ¨
    -0.07
    åĥıåľ¨
    -0.07
    çĤ¹åľ¨
    -0.06
    æĬĬ人
    -0.06
    ä¸¤äººåľ¨
    -0.06
    æĿ¥è¶Ĭ
    -0.06
    é¡¹çĽ®åľ¨
    -0.06
    зÑĥеÑĤ
    -0.06
    POSITIVE LOGITS
     помимо
    0.09
     Pfeffer
    0.08
    çļĦè¿ĺæľī
    0.08
    }]
    0.08
     terdapat
    0.07
    ä¸Ńåı¯ä»¥
    0.07
    åı¯æĢķçļĦæĺ¯
    0.07
    ä¸Ńè¿ĺ
    0.07
    ãģ®ä¸Ńãģ«ãģ¯
    0.07
     ÙĪبÙĬÙĨ
    0.07
    Activations Density 0.434%

    No Known Activations