© 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. 55017
    Prev
    Next
    INDEX
    Explanations

    data storage, metrics, standards, time, duration

    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
    为åħ¶
    -0.07
    |.
    -0.06
    对åħ¶è¿Ľè¡Į
    -0.06
    °.
    -0.06
    为ä¹ĭ
    -0.06
     its
    -0.06
    éķ°
    -0.06
    \Message
    -0.06
    ï½ŀãĢĤ
    -0.06
    ↵↵
    -0.06
    POSITIVE LOGITS
    çļĦ人æĿ¥è¯´
    0.09
    å·¥ä½ľçļĦåIJĮæŶ
    0.08
    ownt
    0.08
    åħ®
    0.08
    лека
    0.08
    éĹ®é¢ĺæŶ
    0.08
     Ãīp
    0.07
    å¦ĤæѤä¹ĭ
    0.07
    imuth
    0.07
    entic
    0.07
    Activations Density 0.657%

    No Known Activations