© 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. 65142
    Prev
    Next
    INDEX
    Explanations

    math and programming keywords

    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
    çĶ¨æľĢ
    -0.08
    urst
    -0.07
    ilar
    -0.07
    istorical
    -0.07
    ering
    -0.07
    dale
    -0.07
    endam
    -0.06
    ÏĨη
    -0.06
    aglio
    -0.06
    åıĬå®īåħ¨
    -0.06
    POSITIVE LOGITS
     lẫn
    0.08
    åĴĮ
    0.08
    reja
    0.07
     maupun
    0.07
    为主
    0.07
    à¹ģละ
    0.07
     chau
    0.07
    acionais
    0.06
    berto
    0.06
    acion
    0.06
    Activations Density 0.034%

    No Known Activations