© 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. 33057
    Prev
    Next
    INDEX
    Explanations

    dispersion and normality

    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
    壮
    -0.08
     instant
    -0.06
    èĥ½è§ģ
    -0.06
    éĩįéĩı
    -0.06
    ä¸į计
    -0.06
    èĥ½å¤Łå®ŀçİ°
    -0.06
    åĨ²
    -0.06
    obook
    -0.06
    asher
    -0.06
    .toLocale
    -0.06
    POSITIVE LOGITS
     outliers
    0.10
     lurking
    0.09
    ardia
    0.08
    æĭŁåIJĪ
    0.08
    ä¸Ń度
    0.08
    ivariate
    0.08
    åĴĮæķ°æį®
    0.08
     skewed
    0.07
     tendencies
    0.07
    ewed
    0.07
    Activations Density 0.020%

    No Known Activations