© 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. 23585
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific texts

    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
    haps
    -0.07
    auer
    -0.07
    ukti
    -0.07
     ÑıкобÑĭ
    -0.07
    chner
    -0.07
    endants
    -0.07
    adini
    -0.07
    å¾·éĩĮ
    -0.06
     appunto
    -0.06
    åİĮ
    -0.06
    POSITIVE LOGITS
    à¹įา
    0.08
    ĩ
    0.07
    =%.
    0.07
    以ä¸ĭ为
    0.07
    âĢİ
    0.07
    staw
    0.07
    以ä¸ĭæĸ¹å¼ı
    0.07
    odem
    0.06
    åıijå±ķåĴĮæĶ¹éĿ©
    0.06
    èµĦæĸĻæĺ¾ç¤º
    0.06
    Activations Density 0.001%

    No Known Activations