© 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. 17391
    Prev
    Next
    INDEX
    Explanations

    cosmological constant problem

    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
    æ±Ĥå®ŀ
    -0.07
    建档ç«ĭåį¡
    -0.07
    åģ¥å£®
    -0.07
     exposing
    -0.07
    è¯Ńè¨ĢçļĦ
    -0.07
    jian
    -0.07
    åįĹé£İ
    -0.07
    rosoft
    -0.07
    xDF
    -0.07
    secutive
    -0.07
    POSITIVE LOGITS
    èĨ¨èĥĢ
    0.08
    常æķ°
    0.08
     Einstein
    0.08
    adel
    0.07
     autop
    0.07
    terra
    0.07
     ìļ°ì£¼
    0.07
     surged
    0.07
    erk
    0.07
    çĪ±åĽłæĸ¯åĿ¦
    0.07
    Activations Density 0.004%

    No Known Activations