© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44881
    Prev
    Next
    INDEX
    Explanations

    December/January or am/pm time stamps

    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
     po
    -0.07
    yt
    -0.06
    éħį
    -0.06
    转
    -0.06
     sou
    -0.06
     qu
    -0.06
     S
    -0.05
     par
    -0.05
     cu
    -0.05
     U
    -0.05
    POSITIVE LOGITS
    ëį°ë¯¸
    0.09
     Fanpage
    0.09
    è´£ç¼ĸ
    0.09
    ftime
    0.08
    åĽŀçŃĶéĩı
    0.08
     âĵĴ
    0.08
    ç¿İ
    0.08
    ниÑĩеÑģÑĤво
    0.08
    SizeMode
    0.08
    æ¹ĸ滨
    0.08
    Activations Density 0.193%

    No Known Activations