© 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. 32085
    Prev
    Next
    INDEX
    Explanations

    increase/decrease/change over time

    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¸ĭä¸ĢæŃ¥
    -0.07
    ulam
    -0.07
    usto
    -0.07
     Besonder
    -0.07
     ute
    -0.07
    ãĤ¤ãĥ¬
    -0.07
    æīĵåĵį
    -0.07
    åľ°ä¹ħ
    -0.07
    è¯¥ç³»ç»Ł
    -0.06
    æ³°
    -0.06
    POSITIVE LOGITS
    åıĺåĮĸ
    0.12
    /change
    0.11
     trend
    0.11
     trends
    0.11
    çļĦåıĺåĮĸ
    0.11
    è¿ĽæŃ¥
    0.11
    åıĺåĮĸçļĦ
    0.11
    è¶ĭåĬ¿
    0.10
    æ¯Ķ以åīį
    0.10
    åıĺè¿ģ
    0.10
    Activations Density 0.383%

    No Known Activations