© 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. 62166
    Prev
    Next
    INDEX
    Explanations

    relative path imports

    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
     Gent
    -0.07
     Daya
    -0.07
    gang
    -0.06
     gent
    -0.06
     Kemp
    -0.06
     ren
    -0.06
    æĸŃçĶµ
    -0.06
    满载
    -0.06
    iko
    -0.06
    çļĦæłĩåĩĨ
    -0.06
    POSITIVE LOGITS
    è´£ç¼ĸ
    0.08
    å¹´æĸ°
    0.08
    çĥŁ
    0.08
    è£ģå®ļ
    0.08
    ä¸ĩåıª
    0.07
    èģ
    0.07
    çħĻ
    0.07
    acce
    0.07
    è·µ
    0.07
    IFO
    0.07
    Activations Density 0.128%

    No Known Activations