© 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. 40860
    Prev
    Next
    INDEX
    Explanations

    relative partners

    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
    ogi
    -0.07
    åĥ
    -0.07
    usto
    -0.07
    èĥĮéĿł
    -0.07
    orien
    -0.07
     Ting
    -0.07
    æĥ®
    -0.07
    篤
    -0.07
    æĬĬå®ĥ们
    -0.07
    å¯ĵ
    -0.07
    POSITIVE LOGITS
    äºİ
    0.11
    æ¯Ķ
    0.09
    ä¸Ĭä¸İ
    0.08
    ä¸İä½ł
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.08
     than
    0.08
    äºİæѤ
    0.08
    issant
    0.08
    äºİ人
    0.08
     ÙĪبÙĬÙĨ
    0.07
    Activations Density 0.261%

    No Known Activations