© 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. 45695
    Prev
    Next
    INDEX
    Explanations

    legal or political situations

    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¿Ŀæ³ķåĴĮä¸įèī¯
    -0.08
    æĬ½æŁ¥æ£ĢæŁ¥
    -0.08
    为ç¥ĸåĽ½
    -0.07
    éĽķåĪ»
    -0.07
    ä¸İèĩªçĦ¶
    -0.07
    ç¥ĸåħĪ
    -0.06
    延年
    -0.06
     endowed
    -0.06
    æĤłä¹ħ
    -0.06
    è¿Ļè¾ĪåŃIJ
    -0.06
    POSITIVE LOGITS
    åIJİç»Ń
    0.12
    äºĭæĢģ
    0.11
     поÑģледова
    0.11
    åIJİç»ŃçļĦ
    0.10
    åIJĦæĸ¹
    0.10
    å¾ĮçºĮ
    0.10
     subsequent
    0.10
    éļıåIJİçļĦ
    0.09
    æŶéĹ´çĤ¹
    0.09
     timeline
    0.09
    Activations Density 1.117%

    No Known Activations