© 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. 30879
    Prev
    Next
    INDEX
    Explanations

    finding something unexpected

    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
    说åĪ°è¿ĻéĩĮ
    -0.08
    åľ¨æĪijå¿ĥä¸Ń
    -0.07
    æĪijçļĦè¯Ŀ
    -0.07
    rag
    -0.06
     gern
    -0.06
     during
    -0.06
    è¿Ļ段è¯Ŀ
    -0.06
    é¸
    -0.06
    adio
    -0.06
    etty
    -0.06
    POSITIVE LOGITS
     ternyata
    0.13
    æĺłåħ¥çľ¼å¸ĺ
    0.12
    ç«Łæĺ¯
    0.12
    åİŁæĿ¥æĺ¯
    0.12
    ç«ŁçĦ¶æĺ¯
    0.12
    赫çĦ¶
    0.12
    æīįåıijçİ°
    0.12
    å±ħçĦ¶æĺ¯
    0.12
     sorpresa
    0.11
    æŀľçĦ¶
    0.11
    Activations Density 0.566%

    No Known Activations