© 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. 23008
    Prev
    Next
    INDEX
    Explanations

    a followed by descriptive word

    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
    ly
    -0.08
    yles
    -0.07
    ful
    -0.07
    éĿĴå¹´çļĦ
    -0.07
    زÙĬ
    -0.07
    las
    -0.07
    losion
    -0.07
    lands
    -0.07
    los
    -0.06
    ¼
    -0.06
    POSITIVE LOGITS
    ervis
    0.08
    ¡
    0.08
    æĵį
    0.08
    chiere
    0.08
    æĽ
    0.07
    èĥ½å¤Łè®©
    0.07
     ejemp
    0.07
    éĺ¿æĭī伯
    0.07
     esclar
    0.07
     foko
    0.07
    Activations Density 0.003%

    No Known Activations