© 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. 57193
    Prev
    Next
    INDEX
    Explanations

    determinative articles "a", "an"

    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
    ä¸İä¼Ĺ
    -0.08
     Minority
    -0.07
     minority
    -0.07
     distinct
    -0.07
     NotImplemented
    -0.06
     Majority
    -0.06
     DISTINCT
    -0.06
    reihe
    -0.06
    avr
    -0.06
    æĺ¯ä¸ĢåĪĩ
    -0.06
    POSITIVE LOGITS
    åĬ¨è¾Ħ
    0.11
    éĿ¢ç§¯çº¦
    0.09
    åĩłåįģä¸ĩ
    0.08
    éĿ¢ç§¯è¾¾
    0.08
    尺寸为
    0.08
     tÃŃ
    0.08
    åĬ¨ä¸įåĬ¨
    0.08
    typ
    0.07
    åĩłåįĥ
    0.07
    åĩłä¸ĩ
    0.07
    Activations Density 0.058%

    No Known Activations