© 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. 32218
    Prev
    Next
    INDEX
    Explanations

    mole percentages

    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
    OrElse
    -0.10
    shire
    -0.09
    ardt
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    ation
    -0.08
    ILT
    -0.08
    erdale
    -0.08
    hend
    -0.08
    nese
    -0.08
    åħ¨å¿ĥåħ¨æĦı
    -0.08
    POSITIVE LOGITS
    olar
    0.08
    æĪĸå°ij
    0.07
    /year
    0.07
    ÙĬد
    0.06
    ilton
    0.06
    /OR
    0.06
    ä¸ŃæŬ
    0.06
    ÙĬÙĨ
    0.06
    plit
    0.06
    volent
    0.06
    Activations Density 0.006%

    No Known Activations