© 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. 60097
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations after 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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼IJ
    -0.07
    æŃ»
    -0.07
    rarian
    -0.06
    æķĻèĤ²è¡ĮæĶ¿éĥ¨éŨ
    -0.06
    å¿ħè¦ģ
    -0.06
    åĽłåľ°
    -0.06
     pokoj
    -0.06
    æ³ķåŃIJ
    -0.06
    .keep
    -0.06
    è²
    -0.06
    POSITIVE LOGITS
     Journal
    0.07
     abstract
    0.07
    åIJĮä¸Ĭ
    0.07
    ç«Ļä¸Ĭ
    0.07
     peer
    0.07
    abstract
    0.07
     Ibid
    0.07
    اعات
    0.06
    heed
    0.06
    -peer
    0.06
    Activations Density 0.082%

    No Known Activations