© 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. 60004
    Prev
    Next
    INDEX
    Explanations

    endings like 'er' or 'og', 'er' followed by certain words

    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
    eer
    -0.07
    e
    -0.07
    ing
    -0.06
    ação
    -0.06
    кен
    -0.06
    ech
    -0.06
    üte
    -0.06
    yper
    -0.06
    -0.06
    aux
    -0.06
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½
    0.09
    ë§ĪìŀIJ
    0.09
    ìį¨
    0.09
     mga
    0.08
    IMUM
    0.08
    дÑĮми
    0.08
    覧
    0.08
    大ä¸Ī夫
    0.08
    ẩm
    0.08
    ä¹ĭåıĪ
    0.08
    Activations Density 0.437%

    No Known Activations