© 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. 32139
    Prev
    Next
    INDEX
    Explanations

    obviously

    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
    æĦıå¤ĸçļĦ
    -0.09
     reportedly
    -0.08
     surprisingly
    -0.08
    ä½łçŁ¥éģĵåIJĹ
    -0.08
    好åĥıåľ¨
    -0.08
     addirittura
    -0.08
    çĶļèĩ³åľ¨
    -0.08
     parfois
    -0.08
     oddly
    -0.08
     optionally
    -0.08
    POSITIVE LOGITS
    èĤ¯å®ļ
    0.11
    å°ijä¸įäºĨ
    0.10
    èĤ¯å®ļæĺ¯
    0.10
    ยà¹Īà¸Ńม
    0.10
    ä¸įè¨ĢèĢĮåĸ»
    0.09
    èĤ¯å®ļä¼ļ
    0.09
    å°±æĺ¯äºĨ
    0.09
    毫æĹłçĸijéĹ®
    0.09
    èĤ¯å®ļè¦ģ
    0.09
     puisqu
    0.09
    Activations Density 0.491%

    No Known Activations