© 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. 40611
    Prev
    Next
    INDEX
    Explanations

    seeking clarification or understanding

    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
    اÙħ
    -0.08
     Sve
    -0.08
    èĢĥèĻijåĪ°
    -0.07
    _symbols
    -0.07
    ABCDEFGHI
    -0.07
    enges
    -0.06
    apters
    -0.06
    .Clock
    -0.06
    åĽłç´łçļĦ
    -0.06
    ]|[
    -0.06
    POSITIVE LOGITS
    é¢ĺæĦı
    0.09
    ä»Ģä¹Īæĺ¯
    0.09
    çĶ¨æĪ·çļĦéľĢæ±Ĥ
    0.08
    æīĢæĮĩ
    0.08
    ä¸ĢåĽŀäºĭ
    0.08
    é¢ĺ缮çļĦ
    0.08
     premise
    0.07
     meant
    0.07
    uet
    0.07
    è¿Ļæĺ¯ä¸ª
    0.07
    Activations Density 0.029%

    No Known Activations