© 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. 55619
    Prev
    Next
    INDEX
    Explanations

    specialized identifiers

    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
    tro
    -0.08
    ffy
    -0.07
    ancies
    -0.07
    天èī²
    -0.07
    ech
    -0.07
    çĴĭ
    -0.07
    å°±åģļ
    -0.07
    trop
    -0.07
    å°±ä¸Ĭ
    -0.07
    UTO
    -0.07
    POSITIVE LOGITS
    plement
    0.08
    å¼ĢåIJİ
    0.08
    åį«
    0.06
    çĤ¹åIJİ
    0.06
    idian
    0.06
    ÙĬد
    0.06
    POINT
    0.06
    (range
    0.06
    å¿ĥåľ°
    0.06
    _lat
    0.06
    Activations Density 0.350%

    No Known Activations