© 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. 59836
    Prev
    Next
    INDEX
    Explanations

    followed by conjunctions or punctuation

    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
    oya
    -0.07
    IfNeeded
    -0.07
    antor
    -0.07
    .dict
    -0.07
    æľĽèijĹ
    -0.07
    TokenType
    -0.07
    Ñĥда
    -0.07
    æŶæŶ
    -0.07
    ]),
    -0.07
    æĹłèĻij
    -0.07
    POSITIVE LOGITS
     accept
    0.08
     seguinte
    0.07
    å¦Ĥä¸ĭ
    0.07
    继ç»Ń
    0.07
     اÙĦتاÙĦÙĬ
    0.07
    åľ¨ä»ĬåIJİ
    0.07
    åħĪåıij
    0.07
     اÙĦتاÙĦÙĬØ©
    0.07
     unread
    0.07
     ÑģледÑĥÑİÑī
    0.07
    Activations Density 0.061%

    No Known Activations