© 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. 58946
    Prev
    Next
    INDEX
    Explanations

    blue

    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
    ä¹īåĭĩ
    -0.07
    otka
    -0.07
    åĬłåĢį
    -0.07
    requently
    -0.07
    ovia
    -0.07
     ëĶ°ë¡ľ
    -0.07
    åĬĽä½ľ
    -0.07
    缸å¾ĹçĽĬå½°
    -0.07
    gat
    -0.07
    åģļèĩªå·±
    -0.07
    POSITIVE LOGITS
    åĵªæĢķæĺ¯
    0.20
    åĵªæĢķ
    0.19
    åį³ä½¿æĺ¯
    0.18
    åį³ä½¿
    0.15
    åį³ä¾¿æĺ¯
    0.15
    åį³ä½¿åľ¨
    0.15
    èĻ½å°ı
    0.14
    —even
    0.14
     albeit
    0.13
     ÑħоÑĤÑĮ
    0.13
    Activations Density 0.208%

    No Known Activations