© 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. 4793
    Prev
    Next
    INDEX
    Explanations

    threshold predicts

    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
    设å¤ĩè¿Ľè¡Į
    -0.08
    çĥŃéŨæIJľç´¢
    -0.07
    verband
    -0.07
     PROPERTY
    -0.07
    Buf
    -0.07
    εÏį
    -0.07
    -property
    -0.07
    海峡两岸
    -0.07
    åħįè´¹åľ¨çº¿
    -0.07
     leef
    -0.07
    POSITIVE LOGITS
    ç¨
    0.08
    èĻŀ
    0.07
    oken
    0.07
    ourcen
    0.07
    ái
    0.07
    ismet
    0.07
     Sez
    0.07
    astos
    0.07
    ¹
    0.06
    orium
    0.06
    Activations Density 0.001%

    No Known Activations