© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17633
    Prev
    Next
    INDEX
    Explanations

    distributed/tests/

    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
    æ²ĥæĸ¯
    -0.07
    æĺ¯ä¸įåı¯
    -0.07
    ommel
    -0.07
    ãģ¤ãĤĤãĤĬ
    -0.07
    Äįių
    -0.07
    á»ĵi
    -0.06
    à¸Īà¹īา
    -0.06
    æĤ¬æŀ¶
    -0.06
    kenntnisse
    -0.06
    egl
    -0.06
    POSITIVE LOGITS
    –and
    0.08
    ä½łæĿ¥
    0.07
    åħ
    0.07
    裳
    0.07
    è¿ģ
    0.06
    lug
    0.06
    lahan
    0.06
    _partial
    0.06
    bung
    0.06
    äºĶæĺŁçº§
    0.06
    Activations Density 0.003%

    No Known Activations