© 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. 38433
    Prev
    Next
    INDEX
    Explanations

    describing actions or states

    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
     thereof
    -0.09
    å¸ĮæľĽå¯¹å¤§å®¶
    -0.09
     deren
    -0.08
     appunto
    -0.07
    åıįèĢĮä¼ļ
    -0.07
    åħ¶ä¸ŃçļĦ
    -0.07
    对å®ĥ
    -0.07
     malah
    -0.07
    åıįèĢĮ
    -0.07
    åºĶæľīçļĦ
    -0.07
    POSITIVE LOGITS
    æ¯ķç«Łæĺ¯
    0.11
    ä¹ĭæīĢ以
    0.11
    çłĶ究表æĺİ
    0.10
     totiž
    0.10
     infatti
    0.10
    说åĪ°åºķ
    0.09
    åĽºçĦ¶
    0.09
     ugyanis
    0.09
    ersatz
    0.09
    ç»Ī究
    0.09
    Activations Density 0.018%

    No Known Activations