© 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. 47687
    Prev
    Next
    INDEX
    Explanations

    what questions

    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
    ä»Ģä¹Īåij¢
    -0.10
     tehát
    -0.09
     ugyanis
    -0.09
     totiž
    -0.08
    究竣æĺ¯
    -0.08
    ,),
    -0.08
    çļĦä¸Ģå®ļ
    -0.08
    ä¸įä»ħåı¯ä»¥
    -0.08
     λοι
    -0.08
     bowiem
    -0.08
    POSITIVE LOGITS
    åħ¶åľ¨
    0.10
    åħ¶ä¸İ
    0.09
    å®ĥ
    0.09
    åħ¶çī¹å¾ģ
    0.09
    å®ĥåľ¨
    0.09
     it
    0.09
     оно
    0.08
     its
    0.08
    æĺ¯åħ¶
    0.08
    åľ¨éĤ£éĩĮ
    0.08
    Activations Density 0.053%

    No Known Activations