© 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. 46188
    Prev
    Next
    INDEX
    Explanations

    fermentation and fermented foods

    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
     laser
    -0.09
    æįī
    -0.08
    çħ¤
    -0.08
    çħ¤çĤŃ
    -0.08
    æ¿Ģåħī
    -0.07
    鹤
    -0.07
    çłļ
    -0.07
    æ´Ĵ水车
    -0.07
     Hughes
    -0.07
    ÙİعÙĴ
    -0.07
    POSITIVE LOGITS
     fermentation
    0.11
     ferment
    0.11
    åıijéħµ
    0.10
    å¾®çĶŁçī©
    0.10
     fermented
    0.09
    æķ´ä¸ªè¿ĩç¨ĭ
    0.09
    è¿Ļ个è¿ĩç¨ĭ
    0.09
     process
    0.08
    process
    0.08
    æŶéĹ´éķ¿
    0.08
    Activations Density 0.058%

    No Known Activations