© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17032
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming

    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
    ìĭľíĶ¼
    -0.07
    resents
    -0.07
    ãģĭãģij
    -0.06
    ***
    -0.06
    ä¼¼çļĦ
    -0.06
    yj
    -0.06
    aight
    -0.06
     somehow
    -0.06
    illac
    -0.06
    ilog
    -0.06
    POSITIVE LOGITS
    ↵↵
    0.07
    &view
    0.07
    iser
    0.07
    dfd
    0.06
    æ°´åĻ¨
    0.06
    ahu
    0.06
    åıĭæĥħæıIJ示
    0.06
    tev
    0.06
    nam
    0.06
     âĨ
    0.06
    Activations Density 0.113%

    No Known Activations