© 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. 62164
    Prev
    Next
    INDEX
    Explanations

    transformation into

    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
    æį·
    -0.07
    ioc
    -0.07
    èĴ¸èĴ¸
    -0.06
     lagi
    -0.06
    æĽĻ
    -0.06
    æĺİæĺİ
    -0.06
     Schro
    -0.06
    çIJī
    -0.06
    æĺİå¾·
    -0.06
    æĺ¯ä»İ
    -0.06
    POSITIVE LOGITS
    转åıĺ为
    0.13
    åıĺ为
    0.13
    转为
    0.12
    åıĺæĪIJ
    0.12
    åıĺæĪIJäºĨ
    0.12
    å°±åıĺæĪIJäºĨ
    0.12
     into
    0.11
    æĶ¹ä¸º
    0.11
    è®ĬæĪIJäºĨ
    0.10
    转åĮĸ为
    0.10
    Activations Density 0.119%

    No Known Activations