© 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. 30749
    Prev
    Next
    INDEX
    Explanations

    hours marking time duration or periods

    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
    itious
    -0.09
     halnya
    -0.09
    etje
    -0.09
    IRECTION
    -0.09
    empre
    -0.08
    æĹ¶æľŁ
    -0.08
    ิà¹īà¸Ļ
    -0.08
    izzy
    -0.08
    ×Ĺת
    -0.08
    ÑģÑĤÑĢойка
    -0.08
    POSITIVE LOGITS
    -hour
    0.09
    /day
    0.08
    -long
    0.08
    iday
    0.08
    elang
    0.07
    髦
    0.07
     hour
    0.07
    -hours
    0.07
    两个å°ıæŶ
    0.07
    worm
    0.07
    Activations Density 0.033%

    No Known Activations