© 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. 34895
    Prev
    Next
    INDEX
    Explanations

    times and dates

    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
    åij¨
    -0.07
    欺
    -0.06
    cato
    -0.06
    ä¸Ģåij¨
    -0.06
     symmetric
    -0.06
    iski
    -0.05
    enko
    -0.05
    è¡Įèµ°
    -0.05
     strong
    -0.05
    ful
    -0.05
    POSITIVE LOGITS
     ë§ŀ춰
    0.09
    affles
    0.09
    åĩĨæŶ
    0.08
    ắm
    0.08
    affle
    0.08
    éIJĺ
    0.08
     fread
    0.08
    ç§ijéĻ¢
    0.08
    èĩªæĪijä»ĭç»į
    0.08
    éģħ
    0.08
    Activations Density 0.144%

    No Known Activations