© 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. 42239
    Prev
    Next
    INDEX
    Explanations

    knew / thought / intention

    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¸Ģ次
    -0.10
    缮åīį
    -0.09
     currently
    -0.09
     tomorrow
    -0.09
     prochain
    -0.09
    åľ¨æİ¥ä¸ĭæĿ¥çļĦ
    -0.09
     now
    -0.08
    æĺİå¹´
    -0.08
     presently
    -0.08
    æĺİ天
    -0.08
    POSITIVE LOGITS
    ä¸ĢçĽ´ä»¥
    0.11
    ä¸Ģ缴
    0.11
     volna
    0.10
    æĹ©æľī
    0.10
    ä¸Ģ缴æĺ¯
    0.10
    æĹ©å°±
    0.10
    æľ¬ä»¥ä¸º
    0.10
    没æĥ³åĪ°
    0.10
    ä¹Łä¸Ģ缴
    0.09
    ä¸ĢçĽ´è¢«
    0.09
    Activations Density 0.645%

    No Known Activations