© 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. 37777
    Prev
    Next
    INDEX
    Explanations

    Proper nouns, titles, and publications

    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
    anch
    -0.07
    ovol
    -0.07
    ç¡®å®ŀ
    -0.07
    å®ĮæĪIJæĬķèµĦ
    -0.07
    ellungen
    -0.07
    æľīä½Ļ
    -0.07
    stry
    -0.06
    æĶ¶èĹıæľ¬ç«Ļ
    -0.06
    çĶĺ
    -0.06
     Garan
    -0.06
    POSITIVE LOGITS
     ìĻ¸ìĹIJëıĦ
    0.09
     اÙĦÙħØ°Ùĥ
    0.08
     übrigens
    0.07
    ฯ
    0.07
     aside
    0.07
    ä»ĸãģ«ãĤĤ
    0.07
    èĻ½æĺ¯
    0.07
     Fallon
    0.06
    пÑĢоÑĩем
    0.06
     ë§IJê³ł
    0.06
    Activations Density 0.558%

    No Known Activations