© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24194
    Prev
    Next
    INDEX
    Explanations

    authors and award-winning books

    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¸ĭèį¯
    -0.07
    untr
    -0.07
    åĬ£
    -0.07
    utig
    -0.07
    æĿ¡æĿ¡
    -0.07
    åIJĦæĸ¹
    -0.07
    æ²»å®ī
    -0.06
     Quartos
    -0.06
    ä¸įé½IJ
    -0.06
    æŃ£ç»Ł
    -0.06
    POSITIVE LOGITS
    æķ£æĸĩ
    0.10
    ä¸Ģä¹Ŀ
    0.09
    ä½ľå®¶
    0.09
    ä½ľèĢħæĺ¯
    0.09
     Nobel
    0.09
    åĵģ读
    0.08
    éĢīèĩª
    0.08
    太太
    0.08
     Pulitzer
    0.08
    é²ģè¿ħ
    0.08
    Activations Density 0.010%

    No Known Activations