© 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. 49816
    Prev
    Next
    INDEX
    Explanations

    distance/between/around

    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
    ascal
    -0.07
    è¶Ĭå¤ļ
    -0.07
     âĨĶ
    -0.07
    缺ä¸Ģä¸įåı¯
    -0.07
     infinitely
    -0.07
    ord
    -0.07
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.07
     âĨIJ
    -0.06
    el
    -0.06
    æľĢç®Ģåįķ
    -0.06
    POSITIVE LOGITS
    约为
    0.12
     around
    0.11
    å¤§çº¦åľ¨
    0.11
    大约
    0.11
    大约æĺ¯
    0.11
    约
    0.10
     ØŃÙĪاÙĦÙĬ
    0.10
    åı¯è¾¾
    0.10
    大æ¦Ĥåľ¨
    0.10
    around
    0.09
    Activations Density 0.074%

    No Known Activations