© 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. 65022
    Prev
    Next
    INDEX
    Explanations

    from mothers

    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
    ä»İ天
    -0.08
    ubs
    -0.07
    å®Į
    -0.06
    å¿ħçľĭ
    -0.06
    æķ°ä»¥
    -0.06
    è§ģè¯Ĩ
    -0.06
    -0.06
    eks
    -0.06
    å°±è¿Ļä¹Ī
    -0.06
     rounded
    -0.06
    POSITIVE LOGITS
    semble
    0.10
    tures
    0.09
    æľīç¦ı
    0.08
    sembles
    0.08
    mix
    0.08
    ationToken
    0.08
    åľ¨åŃ¦ä¹łä¸Ń
    0.08
    elaar
    0.08
     utwor
    0.08
    à¹Ĥà¸ŀ
    0.08
    Activations Density 0.003%

    No Known Activations