© 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. 43797
    Prev
    Next
    INDEX
    Explanations

    when words begin

    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
     affinch
    -0.08
    ambi
    -0.08
    azin
    -0.07
    åľ¨è¿Ļ段æŶéĹ´
    -0.07
     affinché
    -0.07
    å¸Ĥå§Ķå¸ĤæĶ¿åºľ
    -0.07
    enje
    -0.07
    çİĦå¾·
    -0.07
    åĵªéĩĮæľī
    -0.07
    ä¸Ģå¹ķ
    -0.07
    POSITIVE LOGITS
    æĹłè®ºä»İ
    0.10
    å½ĵæĪij们
    0.09
    å¦ĤæŀľçĶ¨
    0.08
    æĹłè®ºæĺ¯
    0.08
     when
    0.08
    åľ¨çĶ¨
    0.08
    å½ĵä½ł
    0.07
    æĮīè§Ħå®ļ
    0.07
    when
    0.07
    æĪijçĶ¨
    0.07
    Activations Density 0.679%

    No Known Activations