© 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. 34863
    Prev
    Next
    INDEX
    Explanations

    rates decreased or increased

    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
    hev
    -0.06
    å°±æĺ¯äºĨ
    -0.06
    åħį费订éĺħ
    -0.06
    èİ·èµŀ
    -0.06
    endam
    -0.06
    æ°Ľ
    -0.06
    ehler
    -0.06
     costing
    -0.06
    å®ŀéĻħçļĦ
    -0.06
    engah
    -0.06
    POSITIVE LOGITS
    éļıçĿĢ
    0.14
    ä¼ļéļıçĿĢ
    0.14
    éļı
    0.13
    éļ¨èijĹ
    0.11
    ä½ĨéļıçĿĢ
    0.11
    éļıçĿĢå¹´é¾Ħ
    0.11
     gradually
    0.11
    éļıçĿĢ社ä¼ļ
    0.10
    éĢIJæ¸IJ
    0.10
    èĢĮéļıçĿĢ
    0.10
    Activations Density 0.063%

    No Known Activations