© 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. 26031
    Prev
    Next
    INDEX
    Explanations

    acetic acid or iodine

    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
    umat
    -0.07
    weit
    -0.06
    åħ³éĶ®
    -0.06
    åľ³
    -0.06
    ä¸Ń使çĶ¨
    -0.06
    æĺ¯ä½¿çĶ¨
    -0.06
    ews
    -0.06
    å¾Ĺ罪
    -0.06
    ä¸įæĥľ
    -0.06
    oltip
    -0.06
    POSITIVE LOGITS
    ä¸įåıij
    0.08
    vertime
    0.08
     ÑĤеÑģÑĤи
    0.08
     testa
    0.08
    ç«£
    0.08
    对è¿Ļ
    0.08
     tester
    0.07
    éĤij
    0.07
    éķĩå®ļ
    0.07
    ãĥĨãĤ¹ãĥĪ
    0.07
    Activations Density 0.008%

    No Known Activations