© 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. 21718
    Prev
    Next
    INDEX
    Explanations

    values

    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
    å¸Ĥ人æ°ijæ³ķéĻ¢
    -0.07
    scha
    -0.07
    адÑĮ
    -0.07
    åħ¶èģĮ
    -0.07
    åĴĮæĶ¹åĸĦ
    -0.07
    ertools
    -0.07
    æĬĢæľ¯æĢ§
    -0.07
    skal
    -0.07
    ãĥªãĤ¨
    -0.07
    Authorized
    -0.06
    POSITIVE LOGITS
    /values
    0.13
     values
    0.13
    -values
    0.12
     Values
    0.12
    Values
    0.11
    _values
    0.11
    ä»·åĢ¼è§Ĥ
    0.11
     ÑĨенноÑģÑĤей
    0.10
     VALUES
    0.10
    values
    0.10
    Activations Density 0.033%

    No Known Activations