© 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. 25548
    Prev
    Next
    INDEX
    Explanations

    First elected

    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
     tw
    -0.08
    ville
    -0.07
    ç·Ĵ
    -0.07
    èĸĩ
    -0.07
    oves
    -0.07
    à§įত
    -0.07
    亲亲
    -0.07
    å±¥
    -0.07
    ç»´åħĭ
    -0.07
     Vit
    -0.07
    POSITIVE LOGITS
    ç¼ĺ
    0.07
    aram
    0.07
    idez
    0.06
    imonio
    0.06
     Tij
    0.06
    åIJ«ç¬ij
    0.06
    ognito
    0.06
    äºĭåįĬåĬŁåĢį
    0.06
    ä¸įæĽ¾
    0.06
     Mazz
    0.06
    Activations Density 0.129%

    No Known Activations