© 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. 2961
    Prev
    Next
    INDEX
    Explanations

    continue

    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
    åľ¨æĥ³
    -0.08
    æµ·æ¶Ľ
    -0.07
    æĢ»æľīä¸Ģ天
    -0.06
    åīįæīĢæľª
    -0.06
    Source
    -0.06
    çªģåĩ»
    -0.06
    éĺ¶
    -0.06
    ipy
    -0.06
    é¦ĸæ¬¡åľ¨
    -0.06
    æºIJäºİ
    -0.06
    POSITIVE LOGITS
    继ç»Ń
    0.14
    åı¯ä»¥ç»§ç»Ń
    0.12
    ãģĿãģ®ãģ¾ãģ¾
    0.12
    继ç»Ńè¿Ľè¡Į
    0.12
    继ç»Ńåľ¨
    0.12
    çķĻåľ¨
    0.11
     continue
    0.11
    继ç»Ń使çĶ¨
    0.11
    continue
    0.11
     continuing
    0.11
    Activations Density 0.319%

    No Known Activations