© 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. 1367
    Prev
    Next
    INDEX
    Explanations

    Ford, unit prefixes, GM, ml, MPa, kilodalton, Leopard

    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
    ãĥ¼ãĤ¹
    -0.08
    erja
    -0.08
    à¥Īया
    -0.08
    ãģĹãĤĥ
    -0.08
    ppo
    -0.08
    pira
    -0.08
    вок
    -0.08
    είÏĦε
    -0.08
    cik
    -0.08
    åľ¨ä»¥åIJİ
    -0.08
    POSITIVE LOGITS
    åį³
    0.09
    ä¹Łå°±æĺ¯
    0.08
    (
    0.07
    çŃīåIJĮäºİ
    0.07
     aka
    0.07
    åį³ä»¥
    0.06
    çŃīåIJĮ
    0.06
     (=
    0.06
     Kred
    0.06
    åį³æĺ¯
    0.06
    Activations Density 0.002%

    No Known Activations