© 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. 16103
    Prev
    Next
    INDEX
    Explanations

    from the, from python, according to

    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
     sillä
    -0.08
    å¦ĤæѤä¹ĭ
    -0.08
    ÙĪسة
    -0.07
    å§ĭçļĩ
    -0.07
    ä¹Łä¸įåı¯
    -0.07
    rå
    -0.07
    erp
    -0.07
    tty
    -0.07
    ospel
    -0.07
    .apple
    -0.07
    POSITIVE LOGITS
    areth
    0.07
     infatti
    0.07
     Against
    0.07
    osse
    0.06
    æķĻåѦç»ıéªĮ
    0.06
    ãģĭãĤĵ
    0.06
    ichen
    0.06
    æĪijæīĢ
    0.06
    ater
    0.06
    andia
    0.06
    Activations Density 0.024%

    No Known Activations