© 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. 7126
    Prev
    Next
    INDEX
    Explanations

    matches words

    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
     Bad
    -0.08
    PHA
    -0.07
    ighth
    -0.07
     Carry
    -0.06
    ä¸ĩ象
    -0.06
    anch
    -0.06
    volv
    -0.06
     Kenn
    -0.06
    bus
    -0.06
    ä¸įå½ĵ
    -0.06
    POSITIVE LOGITS
     matches
    0.08
    adden
    0.08
    urgeon
    0.07
    æĶ¾åľ¨ç¬¬ä¸Ģä½į
    0.07
     Matches
    0.07
    êm
    0.07
    åįĬæŃ¥
    0.07
    axter
    0.07
    ãģ«è¿ijãģĦ
    0.07
    åĮ¹éħį
    0.07
    Activations Density 0.002%

    No Known Activations