© 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. 7282
    Prev
    Next
    INDEX
    Explanations

    packing constraints

    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
     azért
    -0.08
    çļĦéĹ®é¢ĺæĺ¯
    -0.08
     kullanarak
    -0.08
    对äºİè¿Ļ个
    -0.08
    çļĦ缮çļĦæĺ¯
    -0.08
    æĸ¹éĿ¢ä¹Ł
    -0.07
    ä¼ĺçĤ¹æĺ¯
    -0.07
    byname
    -0.07
    çĶ¨äºİ
    -0.07
    è´¹çĶ¨çĶ±
    -0.07
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.12
    èĢĮéĿŀ
    0.11
     rather
    0.11
     chứ
    0.09
    rather
    0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    0.08
     ÙĪÙĦÙĬس
    0.08
    èĢĮå¼Ĥ
    0.07
    åıijå±ķçļĦéľĢè¦ģ
    0.07
    èĢĮå®ļ
    0.07
    Activations Density 0.606%

    No Known Activations