© 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. 61142
    Prev
    Next
    INDEX
    Explanations

    improve, reduce, maximize

    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
    åĻ©
    -0.07
    akan
    -0.07
    ULK
    -0.07
    ä¼ĺç§Ģåħ±äº§åħļåijĺ
    -0.07
    ucci
    -0.07
     Bras
    -0.07
    人æ°ijæĶ¿åºľ
    -0.07
     ramifications
    -0.07
    ä¾Ľ
    -0.07
    ä¸įèĥ½ä½ľä¸º
    -0.06
    POSITIVE LOGITS
    å°ijèµ°
    0.10
     misunderstand
    0.10
     misunderstanding
    0.09
    误解
    0.09
    误ä¼ļ
    0.08
    çIJĨ解
    0.08
    éģ¿éĽ·
    0.08
    çIJĨ解åĴĮ
    0.08
     understanding
    0.08
     confusion
    0.07
    Activations Density 0.202%

    No Known Activations