© 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. 28952
    Prev
    Next
    INDEX
    Explanations

    surfactant

    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
    Ùħت
    -0.06
    isans
    -0.06
    延年
    -0.06
    å¯Ħè¯Ń
    -0.06
     Boul
    -0.06
    æ®ĸ
    -0.06
     timeline
    -0.06
    èİĵ
    -0.06
    穹
    -0.06
     coups
    -0.06
    POSITIVE LOGITS
    soap
    0.10
     detergent
    0.09
     molecules
    0.09
    ä¸įçł´
    0.08
    ä¼ļåĬ¡
    0.08
    æ³³
    0.08
    表éĿ¢æ´»æĢ§
    0.08
    organiz
    0.08
     soap
    0.08
    ãĤ·ãĥ§ãĥ³
    0.08
    Activations Density 0.072%

    No Known Activations