© 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. 51911
    Prev
    Next
    INDEX
    Explanations

    javascript, dot, localhost, anybody

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä»ĸå°±æĺ¯
    -0.08
    azio
    -0.08
    åĪ°åºķæĺ¯
    -0.07
    æĬijæĪĸ
    -0.07
    vier
    -0.07
    hung
    -0.07
    à¸Ńร
    -0.07
    opp
    -0.07
    æľªæľī
    -0.07
    åįĥ家
    -0.07
    POSITIVE LOGITS
    个æĪĸå¤ļ个
    0.09
     infatti
    0.08
    ç¡®å®ŀ
    0.07
    绪
    0.06
    ç¡®
    0.06
    åľŁæĹ¥
    0.06
    åħ¸åŀĭçļĦ
    0.06
    >:</
    0.06
    swick
    0.06
     indeed
    0.06
    Activations Density 0.002%

    No Known Activations