© 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. 7020
    Prev
    Next
    INDEX
    Explanations

    cut-off

    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
    Ł
    -0.07
    .sun
    -0.06
     Kos
    -0.06
    Ú©Ùħ
    -0.06
     [
    -0.06
    äºĨåIJĹ
    -0.06
    HY
    -0.06
     ev
    -0.06
    ä¿¡æģ¯ä¸İ
    -0.06
     Lu
    -0.06
    POSITIVE LOGITS
    åįłåħ¬åı¸
    0.08
    ãģ©ãĤĮ
    0.08
    æĢİä¹ĪåĬŀåij¢
    0.08
    -Methods
    0.08
    ä¸ĩåħĥå·¦åı³
    0.08
    æĢİä¹ĪåĬŀ
    0.08
    ä»Ģä¹ĪæĥħåĨµ
    0.07
    æĢİ麼辦
    0.07
    ÅĽnie
    0.07
    ardon
    0.07
    Activations Density 0.042%

    No Known Activations