© 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. 34266
    Prev
    Next
    INDEX
    Explanations

    will be

    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
    ä½łè¿ĺåľ¨
    -0.08
    audi
    -0.08
    å°ĨæĿ¥
    -0.07
    audit
    -0.07
    deaux
    -0.07
    urre
    -0.07
    Lng
    -0.07
    IfExists
    -0.07
    ecker
    -0.07
    eam
    -0.07
    POSITIVE LOGITS
     undoubtedly
    0.07
    ental
    0.07
     likely
    0.07
    æŃĮ声
    0.07
     probably
    0.07
     be
    0.07
    reno
    0.07
    uera
    0.06
    puter
    0.06
    æł¼çļĦ
    0.06
    Activations Density 0.370%

    No Known Activations