© 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. 33229
    Prev
    Next
    INDEX
    Explanations

    infinite / infinity

    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
    AVA
    -0.07
    haj
    -0.07
    ูà¸ĩ
    -0.07
    prat
    -0.07
    juk
    -0.07
    avig
    -0.07
    èĬĤçļĦ
    -0.07
    çݺ
    -0.07
    ween
    -0.07
    agné
    -0.07
    POSITIVE LOGITS
     infinite
    0.09
    æĹłéĻIJ
    0.07
    Som
    0.07
     Som
    0.07
    æĹłç©·
    0.07
     infinity
    0.07
     infinito
    0.07
     indefinite
    0.07
     infinitely
    0.07
    à¸Ĥà¹īาà¸ĩหà¸Ļà¹īา
    0.07
    Activations Density 0.012%

    No Known Activations