© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30385
    Prev
    Next
    INDEX
    Explanations

    food spoilage and shelf life

    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
    åĨĮ
    -0.07
    -scalable
    -0.07
    åIJĥé¥Ń
    -0.07
    åĨħåIJij
    -0.06
    EMPL
    -0.06
    æĴ¼
    -0.06
    è¸
    -0.06
    (core
    -0.06
    æľīåĬĽ
    -0.06
    åij¼
    -0.06
    POSITIVE LOGITS
    åıĺè´¨
    0.13
    è¿ĩæľŁ
    0.12
    é¾Ħ
    0.11
     expiration
    0.11
    expired
    0.10
     expiry
    0.10
     spoil
    0.10
    expiration
    0.10
     expired
    0.10
    èħIJè´¥
    0.10
    Activations Density 0.062%

    No Known Activations