© 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. 3405
    Prev
    Next
    INDEX
    Explanations

    server driver, cancer therapy, service systems

    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
     appunto
    -0.10
    ä¸ĭåIJĮ
    -0.09
    ãģ®ãģĵãģ¨
    -0.07
     itself
    -0.07
    ier
    -0.07
    æľ¬èº«
    -0.06
     indeed
    -0.06
    PH
    -0.06
     anyway
    -0.06
    ãĥ¶
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.13
     ebenfalls
    0.11
     likewise
    0.10
     ÑĤоже
    0.09
    æĸ¹éĿ¢ä¹Ł
    0.09
     tampoco
    0.09
    亦çĦ¶
    0.09
    ä¹Łæĺ¯å¦ĤæѤ
    0.09
    ä¹Łæĺ¯ä¸Ģæł·
    0.09
    URRE
    0.08
    Activations Density 0.252%

    No Known Activations