© 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. 4651
    Prev
    Next
    INDEX
    Explanations

    pro cons

    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
    inet
    -0.07
    åıª
    -0.06
    èĤ¡
    -0.06
     ÑıкобÑĭ
    -0.06
     uncomment
    -0.06
    anser
    -0.06
    ä¹į
    -0.06
    cs
    -0.06
    åŃ©
    -0.06
    cro
    -0.06
    POSITIVE LOGITS
    æĶ¶èµ·
    0.08
    otime
    0.07
    Printf
    0.07
     Balik
    0.07
     Bring
    0.07
    osit
    0.07
    à¸ķร
    0.07
    åĪ¶èĥľ
    0.07
    ())[
    0.07
    çĿĢèĦ¸
    0.07
    Activations Density 0.001%

    No Known Activations