© 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. 10535
    Prev
    Next
    INDEX
    Explanations

    commas followed by 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
    ãĢģ
    -0.08
    /or
    -0.08
    ç¨ĭ
    -0.06
    acic
    -0.06
    ãĢģãĢİ
    -0.06
    ahl
    -0.06
    ubo
    -0.06
    -or
    -0.06
    akang
    -0.06
    ran
    -0.05
    POSITIVE LOGITS
     and
    0.11
    à¹ģละà¹Ģà¸Ľà¹ĩà¸Ļ
    0.10
    à¹ģละà¸Ħวาม
    0.10
     vÃł
    0.10
    à¹ģละมี
    0.09
     и
    0.09
    à¹ģละ
    0.09
     à¦ıবà¦Ĥ
    0.09
    à¸ĺรรมà¸Ĭาà¸ķิà¹ģละ
    0.09
    å±±éķĩ
    0.09
    Activations Density 0.131%

    No Known Activations