© 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. 47464
    Prev
    Next
    INDEX
    Explanations

    legal and topical names

    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
    åģļæĪIJçļĦ
    -0.07
    åľ¨ä¸º
    -0.07
     ['.
    -0.07
    æĶ¯æĮģä¸ĭ
    -0.07
    mera
    -0.06
    ä¹ĭ以
    -0.06
    åĪ¶æĪIJçļĦ
    -0.06
    Fort
    -0.06
     fo
    -0.06
    wy
    -0.06
    POSITIVE LOGITS
    çĶ¨æīĭæľº
    0.07
    ä¾Ĩèĩª
    0.07
    ezz
    0.07
    çĶ¨çļĦæĺ¯
    0.07
     genom
    0.07
    ä»ĬæľĿ
    0.07
    gradu
    0.07
    åıĹ人
    0.07
    æĿ¥èĩª
    0.07
    çĶ¨æ°´
    0.07
    Activations Density 0.424%

    No Known Activations