© 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. 33451
    Prev
    Next
    INDEX
    Explanations

    time passing or completion

    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
    strt
    -0.08
     Appointment
    -0.07
     Przez
    -0.07
    áĢĻáĢº
    -0.07
    ä»İè¿Ļ个
    -0.07
    uisse
    -0.07
    ÑģÑĤок
    -0.07
    oint
    -0.07
    åľ¨æİ¥ä¸ĭæĿ¥çļĦ
    -0.07
    ÑĦоÑĢа
    -0.07
    POSITIVE LOGITS
     muá»Ļn
    0.09
    after
    0.08
     shortly
    0.08
     midst
    0.08
    before
    0.08
    å°ļæľī
    0.08
    没å¤ļä¹ħ
    0.08
    éĻ·
    0.08
     after
    0.08
     before
    0.08
    Activations Density 0.517%

    No Known Activations