© 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. 4914
    Prev
    Next
    INDEX
    Explanations

    in the

    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
    åĬłåħ³æ³¨
    -0.07
     Anonymous
    -0.07
     wake
    -0.06
    åħ¢åħ¢
    -0.06
    åĽĽåįģ
    -0.06
    çĽ¸äº²
    -0.06
    æĦıåľ¨
    -0.06
    enea
    -0.06
    anonymous
    -0.06
    ibs
    -0.06
    POSITIVE LOGITS
    ç·Ĵ
    0.09
    ä¸ĬåĴĮ
    0.09
    ritz
    0.09
    IGH
    0.08
    æ±Ģ
    0.08
    ogenous
    0.08
    åİŁåĪĽä½ľåĵģ
    0.08
    å§Ĩæĸ¯
    0.07
    adena
    0.07
    åİŁåĪĽæĸĩç«ł
    0.07
    Activations Density 0.006%

    No Known Activations