© 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. 31428
    Prev
    Next
    INDEX
    Explanations

    lists of items or situations

    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
    enga
    -0.08
    amad
    -0.07
     tits
    -0.07
    è¨
    -0.07
    ewan
    -0.07
    TestingModule
    -0.07
    boh
    -0.07
    оÑģо
    -0.06
    .swing
    -0.06
     Dalle
    -0.06
    POSITIVE LOGITS
     situations
    0.09
     circumstances
    0.09
    æĥħå½¢ä¹ĭä¸ĢçļĦ
    0.08
    æĥħåĨµä¸ĭ
    0.07
     warrant
    0.07
    æĺİæĺİ
    0.07
     cad
    0.07
    被è§Ĩ为
    0.07
    esti
    0.07
    ographed
    0.07
    Activations Density 0.035%

    No Known Activations