© 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. 22546
    Prev
    Next
    INDEX
    Explanations

    numbers followed by operators or * tokens

    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
    istique
    -0.07
     cav
    -0.06
    istical
    -0.06
    çļĦæĸ¹æ³ķæĿ¥
    -0.06
    lat
    -0.06
     Lat
    -0.06
    æĸ©
    -0.06
     Stor
    -0.06
    ellan
    -0.06
    enko
    -0.06
    POSITIVE LOGITS
    ä¸įæĶ¾
    0.08
    onet
    0.08
    okrat
    0.08
    pub
    0.08
    обÑĢ
    0.07
    ampo
    0.07
    éĿŀåħ¬
    0.07
    ä¸ĢåĽ¾
    0.07
    ä¸įæį¢
    0.07
    ocrats
    0.07
    Activations Density 0.010%

    No Known Activations