© 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. 18454
    Prev
    Next
    INDEX
    Explanations

    looping through keys

    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
    æĮĩå®ļåľ°çĤ¹
    -0.07
    æ¸Ĭ
    -0.07
    umen
    -0.07
     Lyn
    -0.07
    æĸ¯æĭī
    -0.07
     aspir
    -0.07
    æĿī
    -0.06
    ãĥĥãĤ«ãĥ¼
    -0.06
    ãĤ¹ãĥ¡
    -0.06
    æ²³éĩĮ
    -0.06
    POSITIVE LOGITS
    amakan
    0.08
    impa
    0.07
    ä¸Ģ代
    0.07
    ween
    0.07
    nev
    0.07
     learnt
    0.07
    ÙĨØ´
    0.07
    åľ¨åĶ®
    0.07
    è£ķ
    0.07
    大è¡Ĺ
    0.06
    Activations Density 0.054%

    No Known Activations