© 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. 18020
    Prev
    Next
    INDEX
    Explanations

    suffixes like -ly, -ity, -ization

    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
    istogram
    -0.09
    OrCreate
    -0.08
    istan
    -0.08
    veen
    -0.08
    ldb
    -0.08
    OfType
    -0.08
    æĬĢæľ¯ä¸Ĭ
    -0.08
    ffer
    -0.08
    fam
    -0.07
    WithError
    -0.07
    POSITIVE LOGITS
    åįģ足
    0.10
    åįģ足çļĦ
    0.09
    å¾Ī强çļĦ
    0.09
    åħĥç´łçļĦ
    0.09
     بÙĪدÙĨ
    0.09
    å±ŀæĢ§åĴĮ
    0.08
    åħĥç´ł
    0.08
    å±ŀæĢ§
    0.08
    è¾ĥ强çļĦ
    0.08
    å¼·ãģĦ
    0.08
    Activations Density 0.143%

    No Known Activations