© 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. 49839
    Prev
    Next
    INDEX
    Explanations

    Russian, Arabic, or Polish words

    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
    alani
    -0.07
    weiler
    -0.07
    odont
    -0.07
    çļĦ人éĻħ
    -0.07
    ragen
    -0.07
    aln
    -0.07
    åł
    -0.07
    isz
    -0.06
    waran
    -0.06
    oe
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹ĪçļĦ
    0.08
    criptor
    0.08
    éļıä¹ĭ
    0.07
    hte
    0.07
    ena
    0.07
     ÙħعÙĬÙĨØ©
    0.07
    urna
    0.07
    ms
    0.07
    ÑĥÑīеÑģÑĤво
    0.07
    venida
    0.07
    Activations Density 0.116%

    No Known Activations