© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11810
    Prev
    Next
    INDEX
    Explanations

    barely / sufficient / worthwhile

    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
    æİĴåIJį第ä¸Ģ
    -0.07
     ÙĪاÙĦأس
    -0.07
    æĹłéĻIJ
    -0.07
    好åĥı
    -0.07
    好ä¸į好
    -0.07
    æĹłå°½çļĦ
    -0.07
     Prinz
    -0.07
    ancı
    -0.06
    еди
    -0.06
    ä¸Ģå¸Ĩ
    -0.06
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.11
    足以
    0.10
     even
    0.10
    ä½Ļè£ķ
    0.10
     barely
    0.10
    åĭī强
    0.10
    çĶļèĩ³
    0.10
     (>
    0.09
    è¶³å¤Ł
    0.09
     sufficient
    0.09
    Activations Density 0.285%

    No Known Activations