© 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. 44732
    Prev
    Next
    INDEX
    Explanations

    the other way around

    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
     Schönh
    -0.07
    æŀģ
    -0.07
    åĴĮä¸Ń
    -0.07
    åĸĦ
    -0.06
    lau
    -0.06
    ä¸ĢéĴĪ
    -0.06
    éģ¿
    -0.06
    çŃīéĿŀ
    -0.06
    绣èĬ±
    -0.06
    .nlm
    -0.06
    POSITIVE LOGITS
    åıįè¿ĩæĿ¥
    0.27
     reverse
    0.22
    åıįåIJij
    0.21
    éĢĨåIJij
    0.21
    Reverse
    0.20
     Reverse
    0.20
    reverse
    0.20
     наобоÑĢоÑĤ
    0.20
     vice
    0.19
     inverse
    0.19
    Activations Density 0.143%

    No Known Activations