© 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. 41449
    Prev
    Next
    INDEX
    Explanations

    main x of

    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
    åħ·ä½ĵæĥħåĨµ
    -0.08
    åħ·ä½ĵè¦ģæ±Ĥ
    -0.08
    Ñĥк
    -0.08
    çŃīåħ¶ä»ĸ
    -0.08
    çĶļ
    -0.07
    æĢ»æ¯Ķ
    -0.07
    åħ·ä½ĵæݪæĸ½
    -0.07
     tepatnya
    -0.07
    æŀģäºĨ
    -0.07
    åħ·é«Ķ
    -0.07
    POSITIVE LOGITS
    åĴĮæľĢ
    0.16
    èİ«è¿ĩäºİ
    0.13
     ÙĪØ£Ùĥثر
    0.11
    ä¹Łæĺ¯æľĢ
    0.10
    ä¹ĭä¸Ģ
    0.09
    ä¹ĭä¸ĢçļĦ
    0.09
    ä¹ĭä¸Ģå°±æĺ¯
    0.09
    åĴĮåŁºæľ¬
    0.09
    ä¹ĭä¸Ģæĺ¯
    0.09
    å±ħçĦ¶æĺ¯
    0.08
    Activations Density 0.231%

    No Known Activations