© 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. 12662
    Prev
    Next
    INDEX
    Explanations

    workshops, germ, characteristic, chairman, lightning, three-point, acting

    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
     aka
    -0.08
    被称为
    -0.07
    usband
    -0.07
    Desk
    -0.07
    opedia
    -0.07
    à¸Ħำวà¹Īา
    -0.07
    affen
    -0.07
     sogenannte
    -0.07
    æľīå¦Ĥ
    -0.07
    edy
    -0.07
    POSITIVE LOGITS
    è³ĩ
    0.07
    èĻ«
    0.07
    hte
    0.06
    æĿijåĨħ
    0.06
    溪éķĩ
    0.06
    urator
    0.06
    èµĦ
    0.06
     !
    0.06
    hazi
    0.06
    æĥŁä¸Ģ
    0.06
    Activations Density 0.249%

    No Known Activations