© 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. 42909
    Prev
    Next
    INDEX
    Explanations

    technical words and concepts

    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
     Legend
    -0.08
    åĢ¦
    -0.08
    cona
    -0.08
    Legend
    -0.07
    blad
    -0.07
    大èĩªçĦ¶
    -0.07
     Benghazi
    -0.07
     Havana
    -0.07
     Zapat
    -0.07
    acon
    -0.07
    POSITIVE LOGITS
    åľ¨æĪijåĽ½
    0.15
    åľ¨ä¸ŃåĽ½
    0.13
    à¹ĥà¸Ļà¸Ľà¸£à¸°à¹Ģà¸Ĺศà¹Ħà¸Ĺย
    0.13
    åľ¨ä¸ŃåĽ½çļĦ
    0.13
    à¹ĥà¸Ļà¸Ľà¸£à¸°à¹Ģà¸Ĺศ
    0.12
     Suomessa
    0.12
    åľ¨ç¾İåĽ½
    0.12
     local
    0.12
    æĪijåĽ½çļĦ
    0.11
    æĪijåĽ½
    0.11
    Activations Density 3.295%

    No Known Activations