© 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. 22099
    Prev
    Next
    INDEX
    Explanations

    list transition words

    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
    incy
    -0.07
    ¿
    -0.07
    (es
    -0.07
    à¥Ģल
    -0.07
    iest
    -0.07
     nét
    -0.06
     McCoy
    -0.06
    iett
    -0.06
     {{{
    -0.06
    ysteme
    -0.06
    POSITIVE LOGITS
    æ½®
    0.07
     kac
    0.07
    çļĦæĦıè¯Ĩ
    0.07
    endis
    0.07
    æĦıè¯Ĩ
    0.07
    оÑĢод
    0.07
    clc
    0.07
    _projection
    0.07
     puss
    0.06
    ikle
    0.06
    Activations Density 0.573%

    No Known Activations