© 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. 65149
    Prev
    Next
    INDEX
    Explanations

    meanwhile, back, above, in

    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
    åĩºåıij
    -0.06
    aying
    -0.06
    RA
    -0.06
    XR
    -0.06
    -0.06
    æī¿
    -0.06
    åŀ¢
    -0.06
    ç«Ļèµ·æĿ¥
    -0.06
    å®ŀ
    -0.06
    å·¦åı³
    -0.06
    POSITIVE LOGITS
    asilan
    0.09
    ë²Į
    0.09
    edr
    0.08
    让广大
    0.08
    ανά
    0.08
    mén
    0.08
    è¿ĺæĺ¯ä¸Ģ
    0.08
    agraph
    0.08
    確ãģĭãģ«
    0.08
    æŶ任
    0.08
    Activations Density 0.079%

    No Known Activations