© 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. 51987
    Prev
    Next
    INDEX
    Explanations

    proper nouns: people, companies, technologies

    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
    ÙĨدÛĮ
    -0.07
    ÑĤÑĢе
    -0.06
    adhan
    -0.06
    lesh
    -0.06
    èIJ±
    -0.06
    getResponse
    -0.06
    åĶĩè§Ĵ
    -0.06
    西çľģ
    -0.06
    âī¯
    -0.06
    aeda
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶
    0.10
    åıĬåħ¶
    0.09
    ä½ľä¸º
    0.08
    çī¹æľīçļĦ
    0.08
    ians
    0.08
    åıĬ以ä¸ĭ
    0.08
    aner
    0.08
     stessa
    0.08
    ÄįiÄĩ
    0.07
    ian
    0.07
    Activations Density 0.185%

    No Known Activations