© 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. 4839
    Prev
    Next
    INDEX
    Explanations

    been approached, been used, been done

    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
    ãģªãĤīãģ§ãģ¯ãģ®
    -0.08
    ä¿¡æģ¯çŃī
    -0.07
    acha
    -0.07
    éh
    -0.07
    cé
    -0.07
    åľ¨è·¯ä¸Ĭ
    -0.07
    Assert
    -0.07
    imonial
    -0.07
    zyd
    -0.07
    å·¥ä½ľçļĦåIJĮæŶ
    -0.07
    POSITIVE LOGITS
    åĩłçĤ¹
    0.07
    weise
    0.07
    ains
    0.06
    äºİä¸ĸ
    0.06
    CRET
    0.06
    شرÙĬ
    0.06
    ä¸ŃåĽ½å®¶
    0.06
    alit
    0.06
    åĩłä¸ª
    0.06
    פ×ķ
    0.06
    Activations Density 1.695%

    No Known Activations