© 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. 34216
    Prev
    Next
    INDEX
    Explanations

    submissions, proposals, applications

    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
    éĩĮæĺĤ
    -0.06
    ä¸ŀ
    -0.06
    -sign
    -0.06
    moni
    -0.06
    quetes
    -0.06
    atinum
    -0.06
    çŃ¾åŃĹ
    -0.06
    æľº
    -0.06
     Optik
    -0.06
    æłijä¸Ģ
    -0.06
    POSITIVE LOGITS
    APA
    0.08
    داب
    0.07
    Ïīμα
    0.07
    bö
    0.07
    íľĺ
    0.07
    åij¼
    0.07
    åľ°å¹³
    0.06
     ür
    0.06
    æ½ĩ
    0.06
    adrat
    0.06
    Activations Density 0.001%

    No Known Activations