© 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. 28548
    Prev
    Next
    INDEX
    Explanations

    suffix, later, starting, initial, time

    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
    ajakan
    -0.09
     rong
    -0.08
    mens
    -0.08
    ItemSelected
    -0.08
     تداÙĪÙĦ
    -0.08
     manh
    -0.08
    trut
    -0.08
    veje
    -0.08
    æıIJä¾ĽæĽ´å¥½çļĦ
    -0.08
    -Men
    -0.08
    POSITIVE LOGITS
    ä¸Ģ段æŶéĹ´åIJİ
    0.06
    yp
    0.06
    ä¸įä¹ħ
    0.06
    ä¸Ģ段æŶéĹ´çļĦ
    0.06
    绵
    0.06
    reh
    0.06
    èī¯ä¹ħ
    0.06
     pa
    0.06
    就让
    0.05
    .dc
    0.05
    Activations Density 0.339%

    No Known Activations