© 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. 38275
    Prev
    Next
    INDEX
    Explanations

    a, b, c, 1, 2, 3

    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
    hun
    -0.08
    .idea
    -0.08
    nish
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.07
    çļĦäºĭäºĨ
    -0.07
    åķ¸
    -0.07
    à®Łà¯Ī
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    åıĪä½ķ
    -0.07
    old
    -0.07
    POSITIVE LOGITS
    å®ĥæĺ¯ä¸Ģç§į
    0.08
    å¾ĹåIJį
    0.08
    åı¯ä»¥åĪĨ为
    0.07
    æĢ§æĺ¯
    0.07
    owed
    0.07
    èµ·æºIJäºİ
    0.07
    å®ĥæĺ¯
    0.07
    èĭ¥
    0.07
    åı¯ä»¥æł¹æį®
    0.06
    åı¯ä»¥å°Ĩ
    0.06
    Activations Density 0.005%

    No Known Activations