© 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. 29397
    Prev
    Next
    INDEX
    Explanations

    convergence and limits

    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
    è°ĥåĬ¨
    -0.09
    Ĥ¹
    -0.09
    imson
    -0.08
    ä½łæĺ¯æĪij
    -0.08
    oulder
    -0.08
    .sym
    -0.08
    GRAM
    -0.08
    ABEL
    -0.08
    Ø´Ùħ
    -0.08
     пеÑĢеÑģе
    -0.08
    POSITIVE LOGITS
     infinite
    0.08
    æŀģéĻIJ
    0.07
    éĢ¼è¿ij
    0.07
    sequence
    0.07
    æĹłéĻIJ
    0.07
    æĹłç©·
    0.07
    ilon
    0.07
     Ces
    0.07
     convergence
    0.07
     asympt
    0.07
    Activations Density 0.058%

    No Known Activations