© 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. 33193
    Prev
    Next
    INDEX
    Explanations

    ketones or ketogenic

    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
    otin
    -0.10
    canf
    -0.09
    ively
    -0.09
    klet
    -0.08
    ANCEL
    -0.08
    yks
    -0.08
    aging
    -0.08
    taki
    -0.08
    tır
    -0.08
    tabel
    -0.08
    POSITIVE LOGITS
    ben
    0.07
    uxtap
    0.07
    weed
    0.07
    deaux
    0.07
    /
    0.06
    oulouse
    0.06
    sters
    0.06
    ification
    0.06
    venes
    0.06
    ยà¸Ļà¸ķà¹Į
    0.06
    Activations Density 0.007%

    No Known Activations