© 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. 42352
    Prev
    Next
    INDEX
    Explanations

    Chinese text indicators

    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
    è¿ĺæľīåħ¶ä»ĸ
    -0.07
    -0.07
    1
    -0.06
     other
    -0.06
    ↵
    -0.06
    waran
    -0.05
    为äºĨæĽ´å¥½çļĦ
    -0.05
    H
    -0.05
    çħĮ
    -0.05
    å¿ħè¦ģæŶ
    -0.05
    POSITIVE LOGITS
    ä¸Ģæĸ¹éĿ¢
    0.09
    æľ¬å¸ĸ
    0.09
    解éĩĬ说
    0.08
    ä¸įä»ħèĥ½å¤Ł
    0.08
    ä¸Ńè¶ħ
    0.08
    $",
    0.08
    èĻ½çĦ¶åľ¨
    0.08
    é¦ĸåħĪåľ¨
    0.08
    ä¸ĢæĶ¹
    0.08
    åĪ«çľĭ
    0.08
    Activations Density 0.008%

    No Known Activations