© 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. 64935
    Prev
    Next
    INDEX
    Explanations

    fructose and related sugars

    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
    rest
    -0.07
    éĢĢ
    -0.07
    æ¡£
    -0.06
    è¿ĩçļĦ
    -0.06
    ipel
    -0.06
    ä¸įéĢĢ
    -0.06
    rent
    -0.06
    ata
    -0.06
    平淡
    -0.06
    éĢĢäºĨ
    -0.06
    POSITIVE LOGITS
    onan
    0.08
    ohan
    0.08
    irão
    0.08
    ohana
    0.08
    enstein
    0.08
     sugars
    0.08
    _CID
    0.08
    esak
    0.08
    gire
    0.08
    ç³ĸæµĨ
    0.08
    Activations Density 0.009%

    No Known Activations