© 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. 50834
    Prev
    Next
    INDEX
    Explanations

    then

    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
    à¸ŀาà¸Ļ
    -0.08
    uyer
    -0.07
    æĽ´æ³¨éĩį
    -0.07
    ä¸įåĥı
    -0.07
     myself
    -0.07
    çį¨
    -0.07
    çĭ¬
    -0.07
    uchos
    -0.07
    atti
    -0.07
    aque
    -0.07
    POSITIVE LOGITS
    è°ĵä¹ĭ
    0.09
    称为
    0.08
    ilha
    0.07
    æľīèĩ´
    0.07
    åį³ä¸º
    0.07
    称ä¹ĭ为
    0.07
    äºĶèī²
    0.07
    被称为
    0.07
    åĨįè§ģ
    0.06
    éĤ£ä½łå°±
    0.06
    Activations Density 0.045%

    No Known Activations