© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60975
    Prev
    Next
    INDEX
    Explanations

    to followed by a verb

    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
    none
    -0.08
    not
    -0.08
    enge
    -0.08
     none
    -0.07
    ist
    -0.07
    以ä¸ĭåĩłä¸ª
    -0.06
    ik
    -0.06
    æİ¥åıĹçļĦ
    -0.06
    ito
    -0.06
    åĴĮ幸ç¦ı
    -0.06
    POSITIVE LOGITS
    æĥ®
    0.08
    ä¸įçŁ¥éģĵä½ł
    0.08
    å¾ĹåĪ°ä¸Ģ个
    0.08
    éĥ½è§īå¾Ĺ
    0.08
    å¾ĹåĪ°æľīæķĪ
    0.07
    ynd
    0.07
    dami
    0.07
    formas
    0.07
    =>
    0.07
    樽
    0.07
    Activations Density 0.029%

    No Known Activations