© 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. 28365
    Prev
    Next
    INDEX
    Explanations

    infinite vector spaces

    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
    ä¸į误
    -0.09
    çIJ¥
    -0.09
    ç»ļ
    -0.08
    angkap
    -0.08
    éłĵ
    -0.08
    ROUTE
    -0.07
    _quick
    -0.07
    á»ĩ
    -0.07
    CAST
    -0.07
     Furious
    -0.07
    POSITIVE LOGITS
     infinite
    0.12
     infinitely
    0.10
    æĹłéĻIJ
    0.09
    æĹłéĻIJçļĦ
    0.09
     indefinite
    0.09
     Infinite
    0.09
     unlimited
    0.08
     indefinitely
    0.08
    æĹłç©·çļĦ
    0.08
    æĹłæŃ¢
    0.08
    Activations Density 0.013%

    No Known Activations