© 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. 8934
    Prev
    Next
    INDEX
    Explanations

    possessive nouns ending in 's

    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
    (([
    -0.07
    ills
    -0.07
    heet
    -0.07
    ish
    -0.06
    ream
    -0.06
    Bits
    -0.06
    enheim
    -0.06
    注åĨĮçĶ¨æĪ·
    -0.06
    ä¹İ
    -0.06
    åĴ¨
    -0.06
    POSITIVE LOGITS
    alaus
    0.09
    è°ģæĺ¯
    0.08
    ÅĽci
    0.07
    ertino
    0.07
    gars
    0.07
    acin
    0.07
    å¸ĥæŀĹ
    0.07
    istin
    0.07
    vern
    0.07
    æĺ¯è°ģ
    0.07
    Activations Density 0.002%

    No Known Activations