© 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. 37473
    Prev
    Next
    INDEX
    Explanations

    law enforcement department

    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
     Wend
    -0.06
    GT
    -0.06
    ++
    -0.06
    ha
    -0.06
     RPM
    -0.06
     Flash
    -0.06
    ust
    -0.06
    赤
    -0.06
    otten
    -0.06
    è¿İé£İ
    -0.06
    POSITIVE LOGITS
    rael
    0.08
    mor
    0.08
     Investigators
    0.08
    çĤ¹åĩ»ä¸Ĭæĸ¹èĵĿåŃĹ
    0.07
     MEDIA
    0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    0.07
    oples
    0.07
     à¹Ģà¸ķร
    0.07
     Investig
    0.07
    agraph
    0.07
    Activations Density 0.266%

    No Known Activations