© 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. 50651
    Prev
    Next
    INDEX
    Explanations

    code block openers

    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
    ments
    -0.10
    มà¸Ļ
    -0.10
    son
    -0.09
    mann
    -0.09
    ãĥ³
    -0.09
    ÙĨÛĮÙĨ
    -0.08
    irchen
    -0.08
    ÙĨ
    -0.08
    ë¥ł
    -0.08
    uration
    -0.08
    POSITIVE LOGITS
    ligh
    0.08
     {//
    0.08
    åŃļ
    0.07
     {
    0.07
    à¸Ħวาม
    0.07
     bahwa
    0.07
    วà¹Īา
    0.07
    âĢ¦âĢ¦ãĢĤ
    0.07
     (*((
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    Activations Density 0.114%

    No Known Activations