© 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. 51219
    Prev
    Next
    INDEX
    Explanations

    article followed by a noun

    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
    ä½łä»¬éĥ½
    -0.08
    éļħ
    -0.08
    mojom
    -0.08
    /o
    -0.07
    她便
    -0.07
    æĸĩç«łäºĨ
    -0.07
    altungs
    -0.07
     zugesch
    -0.07
    agogue
    -0.07
    imente
    -0.07
    POSITIVE LOGITS
     however
    0.08
    æľī趣çļĦæĺ¯
    0.08
    omi
    0.08
    âĹĩâĹĨ
    0.08
    å½ĵçĦ¶
    0.08
    尽管å¦ĤæѤ
    0.07
     furthermore
    0.07
    ä¸įåIJĮçļĦæĺ¯
    0.07
    è¦ģ注æĦıçļĦæĺ¯
    0.07
    éģĹæĨ¾çļĦæĺ¯
    0.07
    Activations Density 1.909%

    No Known Activations