© 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. 57822
    Prev
    Next
    INDEX
    Explanations

    achievements and progress

    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
    åĴĮ家éķ¿
    -0.08
    ulet
    -0.08
    åıĬ家éķ¿
    -0.07
    åŃļ
    -0.07
    familien
    -0.07
     سرا
    -0.07
    ={({
    -0.07
     lagun
    -0.06
    uas
    -0.06
    ulator
    -0.06
    POSITIVE LOGITS
    áŀļáŀĶ
    0.13
     milik
    0.12
     ÙĦدÙī
    0.12
    à¸Ĥà¸Ńà¸ĩà¸ľà¸¹à¹ī
    0.11
     bagi
    0.10
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.10
     chez
    0.10
    สำà¸Ħัà¸įà¸Ĥà¸Ńà¸ĩ
    0.09
     dimiliki
    0.09
     isteyen
    0.09
    Activations Density 0.786%

    No Known Activations