© 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. 7127
    Prev
    Next
    INDEX
    Explanations

    check script, price, or correctness

    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
    ushman
    -0.08
    ynchronously
    -0.08
    çIJ¥
    -0.08
    rowse
    -0.07
    çī¹å®ļçļĦ
    -0.07
    returnValue
    -0.07
    Ïģν
    -0.07
     beze
    -0.07
    Routine
    -0.07
    addock
    -0.07
    POSITIVE LOGITS
    ÑijÑĤ
    0.07
     bahwa
    0.07
     correctness
    0.07
    otan
    0.07
    ä¸Ģä¸ĭ
    0.07
    è¶Ĭèµ°è¶Ĭ
    0.06
     {}:
    0.06
    æ»¡çĽ®
    0.06
     Cunningham
    0.06
     usage
    0.06
    Activations Density 0.002%

    No Known Activations