© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7234
    Prev
    Next
    INDEX
    Explanations

    use of the word "phrase"

    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
    s
    -0.09
    åĬłæĭ¿å¤§
    -0.08
    ÑĦан
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    wards
    -0.08
    æĸ°åĬłåĿ¡
    -0.08
    çīĩçīĩ
    -0.07
    unda
    -0.07
    нÑĥÑģ
    -0.07
    اÙĦÙģ
    -0.07
    POSITIVE LOGITS
    новÑĮ
    0.09
    ÙĬÙĨ
    0.08
    ette
    0.07
    stuk
    0.07
    ÙĪارÙĩ
    0.07
    witz
    0.07
    ãĥ³ãĤ°
    0.07
    ovolta
    0.07
    hift
    0.07
    æīĢæĮĩ
    0.07
    Activations Density 0.005%

    No Known Activations