© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14167
    Prev
    Next
    INDEX
    Explanations

    am working

    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
    çļĦå°±æĺ¯
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.07
     liá»ģn
    -0.07
    çļĦ两
    -0.06
    oron
    -0.06
    orie
    -0.06
    å°±ä¸įæĺ¯
    -0.06
    ĩ
    -0.06
    proved
    -0.06
    æĸ°çļĦä¸Ģ
    -0.06
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.11
    åIJĦèĩª
    0.10
    åIJĦæľī
    0.10
    ãģ¨ãĤĤãģ«
    0.09
    åħ±ãģ«
    0.08
    ãģĿãĤĮãģŀãĤĮ
    0.08
     themselves
    0.08
     nhau
    0.08
     respectively
    0.08
    ä¸ĭåIJĮ
    0.08
    Activations Density 0.002%

    No Known Activations