© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 45089
    Prev
    Next
    INDEX
    Explanations

    hypotheses, options, ways

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çħ§æł·
    -0.08
    ãn
    -0.08
    æŀĦéĢł
    -0.07
    å®Įæľ¬å°ı说
    -0.07
    没æľīéĤ£ä¹Ī
    -0.07
    æľīæĽ´å¤ļçļĦ
    -0.06
    èİ·å¾ĹæĽ´å¤ļçļĦ
    -0.06
    æĽ´è¦ģ
    -0.06
    å°½åı¯èĥ½
    -0.06
    æĬĢæľ¯éĹ®é¢ĺ
    -0.06
    POSITIVE LOGITS
    æĺ¾èĢĮæĺĵè§ģ
    0.08
     казалоÑģÑĮ
    0.08
    çľĭä¼¼
    0.07
    åIJ¬èµ·æĿ¥
    0.07
    ä¹į
    0.07
    oczy
    0.07
    æŃ£ç¡®çŃĶæ¡Ī
    0.07
     Ñģом
    0.07
    å¾Īæĺİæĺ¾
    0.07
    dsm
    0.07
    Activations Density 0.002%

    No Known Activations