© 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. 52032
    Prev
    Next
    INDEX
    Explanations

    represented by

    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
    antin
    -0.08
    ä¸Ģæĸ°
    -0.07
    InBackground
    -0.07
    amientos
    -0.07
    cheng
    -0.07
    æĬĬ人
    -0.07
    _mut
    -0.07
    ToUpdate
    -0.07
    hevik
    -0.07
    åıĸæ¶ĪäºĨ
    -0.07
    POSITIVE LOGITS
    ä½ĵçİ°åľ¨
    0.08
    ä¿ĿåŃĺåľ¨
    0.08
    åĩºçİ°åľ¨
    0.08
    åŃĺåľ¨äºİ
    0.08
    åĩºçİ°åľ¨äºĨ
    0.07
    纶
    0.07
    æĿł
    0.07
     represented
    0.07
    (!(
    0.07
    é¦ĸæ¬¡åľ¨
    0.07
    Activations Density 0.212%

    No Known Activations