© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51998
    Prev
    Next
    INDEX
    Explanations

    format and design

    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
    Negative Logits
    erma
    -0.07
     rowNum
    -0.07
    shore
    -0.07
     selengkapnya
    -0.07
    æĥ³æĸ¹
    -0.07
    /mit
    -0.07
    oja
    -0.07
    visor
    -0.07
    ernet
    -0.07
    å§ĶåĨħ
    -0.07
    POSITIVE LOGITS
    åĴĮåĨħ容
    0.10
    åĴĮéĩįçĤ¹
    0.07
    combe
    0.07
    åĴĮæĸ¹æ³ķ
    0.07
     format
    0.07
    æ¦Ĩ
    0.07
    gada
    0.06
     بÙĨدÛĮ
    0.06
    uala
    0.06
     manner
    0.06
    Activations Density 0.023%

    No Known Activations