© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23185
    Prev
    Next
    INDEX
    Explanations

    ago or after time units

    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
     Lees
    -0.08
    å®Īä¿¡
    -0.08
    ä¸į被
    -0.07
    ç»ĵæŀľæĺ¯
    -0.07
    åįĬè¾¹
    -0.07
    adol
    -0.07
    ×Ļ׳×ķ
    -0.07
    AndWait
    -0.07
    æĹ©æĻļ
    -0.07
    gaste
    -0.07
    POSITIVE LOGITS
     away
    0.09
    ually
    0.08
    æ¯Ķä½ł
    0.08
     diferença
    0.07
     ahead
    0.07
    è·Ŀ离
    0.07
    æ¯Ķ
    0.07
     distance
    0.07
    ä¹ĭéģ¥
    0.07
    ä¸İä¼Ĺä¸įåIJĮ
    0.07
    Activations Density 0.283%

    No Known Activations