© 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. 38097
    Prev
    Next
    INDEX
    Explanations

    Ising model, Saint-Michel, Cart, thousands, efficacy

    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
    onger
    -0.07
    heden
    -0.07
    جÙĪ
    -0.07
    èĪįä¸įå¾Ĺ
    -0.07
    æ¶İ
    -0.06
    å°¾
    -0.06
    æľīè´£
    -0.06
    umon
    -0.06
    weiler
    -0.06
    æľ¬é¢ĺåĪĨæŀIJ
    -0.06
    POSITIVE LOGITS
    endor
    0.08
    çªģåĩ»
    0.08
     midway
    0.08
    平价
    0.07
    佬
    0.07
    .eval
    0.07
    éĺµèIJ¥
    0.07
    anes
    0.07
    è¿Ļ两ç§į
    0.07
     inaugur
    0.07
    Activations Density 0.002%

    No Known Activations