© 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. 24539
    Prev
    Next
    INDEX
    Explanations

    part of

    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
    egn
    -0.08
    azia
    -0.08
    åįĥåįĥ
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    é¾ĻæĹı
    -0.07
    жнее
    -0.07
    åįĥ
    -0.07
    çĥŃéŨæĸĩç«ł
    -0.07
    稳å¢ŀéķ¿
    -0.07
    AYER
    -0.07
    POSITIVE LOGITS
    สำà¸Ħัà¸įà¸Ĥà¸Ńà¸ĩ
    0.12
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    0.12
    æĺ¯è¯¥
    0.11
    åľ¨è¯¥
    0.10
    à¹ģรà¸ģà¸Ĥà¸Ńà¸ĩ
    0.10
    à¹Ģà¸Ļืà¹īà¸Ńหาà¸Ĥà¸Ńà¸ĩ
    0.09
    为该
    0.09
    สà¹Īวà¸Ļà¸Ĥà¸Ńà¸ĩ
    0.09
    à¹ĥหมà¹Īà¸Ĥà¸Ńà¸ĩ
    0.09
     della
    0.09
    Activations Density 1.073%

    No Known Activations