© 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. 22327
    Prev
    Next
    INDEX
    Explanations

    infinity and endlessness

    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
    åIJĮ声
    -0.08
    夯
    -0.08
    夯å®ŀ
    -0.08
    ä¸ĢæĹģ
    -0.07
    ç²Ĺæļ´
    -0.07
    人å¤ļ
    -0.07
    ulpt
    -0.07
    memcmp
    -0.07
    ç¦ıæĺŁ
    -0.07
    亲
    -0.07
    POSITIVE LOGITS
     infinite
    0.11
    æĹłç©·
    0.10
    æĹłå°½
    0.10
    Infinity
    0.09
    æĹłéĻIJ
    0.09
     Infinity
    0.09
     infinity
    0.09
     Infinite
    0.09
     infinitely
    0.08
     endless
    0.08
    Activations Density 0.030%

    No Known Activations