© 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. 7098
    Prev
    Next
    INDEX
    Explanations

    create or insert action

    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
    itos
    -0.08
    ä¸įä¹±
    -0.08
    Updater
    -0.07
    çĴ§
    -0.07
    {o
    -0.07
    íļĮìĿĺ
    -0.06
    iced
    -0.06
    formed
    -0.06
    efined
    -0.06
    izada
    -0.06
    POSITIVE LOGITS
    OrUpdate
    0.11
     succeeded
    0.08
    ä¸įäºĨçļĦ
    0.07
    åĴĮåıijå±ķ
    0.07
    OrCreate
    0.07
    åıĸå¾Ĺæĸ°
    0.07
    çīŁå°¼
    0.07
    ahnya
    0.07
    失败
    0.07
    åĴĮè°ĥæķ´
    0.07
    Activations Density 0.179%

    No Known Activations