© 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. 4154
    Prev
    Next
    INDEX
    Explanations

    year and day patterns

    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
    kker
    -0.06
    remen
    -0.06
    èļĤ
    -0.06
    olak
    -0.06
    æıIJèµ·åħ¬è¯ī
    -0.06
    agan
    -0.06
    ä¹į
    -0.06
    ÙĬاÙĨ
    -0.06
    ken
    -0.06
    rous
    -0.06
    POSITIVE LOGITS
    æµ·é»ĺ
    0.09
    inne
    0.08
    ster
    0.07
    uter
    0.07
    artal
    0.07
     fray
    0.07
    å®Ŀé¾Ļ
    0.07
     Gì
    0.07
     cÆ°á»Ľc
    0.07
    è¯¥ä½ľèĢħ
    0.07
    Activations Density 0.218%

    No Known Activations