© 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. 23996
    Prev
    Next
    INDEX
    Explanations

    States a from its FROM is FROM

    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
    æ¯ıä¸Ģ个åѦçĶŁ
    -0.08
    ogo
    -0.07
    éĻIJåĪ¶æ¶Īè´¹
    -0.07
    _Internal
    -0.07
    ä½Ļå¹´
    -0.07
    åĩłä¸ªæĸ¹éĿ¢
    -0.07
    åIJĦæł¡
    -0.07
    çĶ³è¯·èĢħ
    -0.07
    äºİæĺ¯åľ¨
    -0.07
    ÑĤили
    -0.07
    POSITIVE LOGITS
    å¾µ
    0.07
    çİĭçİī
    0.07
    èĢĮä¸Ķæĺ¯
    0.07
    achu
    0.06
    æ¤
    0.06
    å½ĵçĦ¶æĺ¯
    0.06
     primarily
    0.06
    én
    0.06
    ä¸Ģæĺ¯
    0.06
    åĸ½
    0.06
    Activations Density 0.001%

    No Known Activations