© 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. 21631
    Prev
    Next
    INDEX
    Explanations

    records and season outcomes

    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
    anium
    -0.07
    oš
    -0.07
    ç«ŁçĦ¶
    -0.07
    _IMPL
    -0.07
    º¼
    -0.06
    {_
    -0.06
    çĶ¨æĪ·çļĦéľĢæ±Ĥ
    -0.06
     User
    -0.06
    ä»ĸç«ŁçĦ¶
    -0.06
    ç«ŁçĦ¶æĺ¯
    -0.06
    POSITIVE LOGITS
    æĶ¶
    0.07
    ãĤĥ
    0.07
    arno
    0.07
    大ä¸ĸçķĮ
    0.07
    /operators
    0.07
    endid
    0.07
     Galli
    0.07
    unde
    0.07
    __$
    0.07
    æ³ķå®ļ
    0.07
    Activations Density 0.060%

    No Known Activations