© 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. 37613
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

    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
    èħ°
    -0.08
    alidad
    -0.07
    ä¸Ģç»ı
    -0.07
    foot
    -0.07
    大ä¸Ń
    -0.07
    åĪĩ身åĪ©çĽĬ
    -0.07
    tori
    -0.07
    çŁ¾
    -0.07
    åıįæŃ£
    -0.07
    EMPL
    -0.06
    POSITIVE LOGITS
    åĪĨ为
    0.15
    åĪĨçĤº
    0.12
    æĹ¢æľī
    0.12
    çļĦ两个
    0.12
    åı¯ä»¥åĪĨ为
    0.12
    åı¯åĪĨ为
    0.11
    åĪĨæĪIJ
    0.11
    åĪĨåĪ«
    0.11
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļà¸Ķà¹īวย
    0.11
    åĪĨåĪ¥
    0.11
    Activations Density 0.195%

    No Known Activations