© 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. 30556
    Prev
    Next
    INDEX
    Explanations

    improve or specify

    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
    ãĥ¼ãĥĦ
    -0.08
    ä½Ĩå®ĥ们
    -0.08
    模æĭŁè¯ķé¢ĺ
    -0.08
    她èĩªå·±
    -0.07
    /of
    -0.07
    éĺħè¯»æľ¬æĸĩ
    -0.07
    кÑĥÑĢ
    -0.07
    æİĤ
    -0.07
    _BOTH
    -0.07
    /from
    -0.07
    POSITIVE LOGITS
    uje
    0.08
    ä¸Ģä¸ĭ
    0.07
     dulu
    0.07
    ä¸ĢäºĮ
    0.07
    indo
    0.07
     accordingly
    0.06
     olaraq
    0.06
     with
    0.06
    inya
    0.06
     into
    0.06
    Activations Density 0.025%

    No Known Activations