© 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. 4689
    Prev
    Next
    INDEX
    Explanations

    code literals

    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
    å®ŀè¯Ŀ
    -0.08
    åŁ¹åħ»åĴĮ
    -0.07
    ä½ľæ³ķ
    -0.07
    è°¤
    -0.07
    ap
    -0.07
    欣èµıåĪ°
    -0.07
    åı°è¯į
    -0.06
    apot
    -0.06
     trans
    -0.06
    lay
    -0.06
    POSITIVE LOGITS
    yai
    0.09
    _literals
    0.08
    leden
    0.07
    Ú¯ÙĦ
    0.07
    iseur
    0.07
    伶ä¿IJ
    0.07
    微信æī«ä¸Ģæī«
    0.07
    à¹Ħà¸ĩ
    0.07
    zil
    0.07
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.07
    Activations Density 0.025%

    No Known Activations