© 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. 59855
    Prev
    Next
    INDEX
    Explanations

    one day I

    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
    æľ¬è½®
    -0.08
    ä¸ĢæĹģ
    -0.08
     INFOR
    -0.08
    sis
    -0.08
    çļĦéĥ½æĺ¯
    -0.07
    ıŁ
    -0.07
    ÑģÑģа
    -0.07
    FTER
    -0.07
    ä¸Ģè·¯ä¸Ĭ
    -0.07
    dek
    -0.07
    POSITIVE LOGITS
     occasion
    0.09
    çī¹åĪ«æĺ¯åľ¨
    0.08
    次çļĦ
    0.08
    次æķ°
    0.08
    eel
    0.07
    occasion
    0.07
    -times
    0.07
    éĹ²æļĩ
    0.07
     spontaneous
    0.07
    訪
    0.07
    Activations Density 0.278%

    No Known Activations