© 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. 55373
    Prev
    Next
    INDEX
    Explanations

    insert into or to

    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
    å®ĥçļĦ
    -0.07
    ette
    -0.07
    å®ĥåľ¨
    -0.06
    ä¸įåĢ¼å¾Ĺ
    -0.06
    以åıĬä¸ĢäºĽ
    -0.06
     Its
    -0.06
    ä¸įåĢ¼
    -0.06
    被人们
    -0.06
    ubar
    -0.06
     its
    -0.06
    POSITIVE LOGITS
    клада
    0.10
    º¼
    0.08
    转载请注æĺİ
    0.08
    æķĪæŀľæĽ´å¥½
    0.08
    ẹt
    0.08
    зо
    0.08
    -progress
    0.08
    ç´łæľī
    0.08
    érc
    0.08
    träg
    0.07
    Activations Density 0.177%

    No Known Activations