© 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. 65174
    Prev
    Next
    INDEX
    Explanations

    give, subscription, during, ATT

    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
    ang
    -0.09
    -0.08
    akh
    -0.08
    ERT
    -0.07
    -0.07
    è¿ĩäºİ
    -0.07
    ert
    -0.07
    è¥
    -0.07
    EntryPoint
    -0.06
    èĮ¬
    -0.06
    POSITIVE LOGITS
    clipse
    0.07
    CIO
    0.07
    endien
    0.07
    eor
    0.07
    çİ°ä½ı
    0.07
    evere
    0.07
    reeze
    0.07
    uttle
    0.07
    eza
    0.07
    ÑģиÑı
    0.07
    Activations Density 0.003%

    No Known Activations