© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48310
    Prev
    Next
    INDEX
    Explanations

    learning goals and objectives

    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
    ä¾µ
    -0.08
    ovich
    -0.08
    aksin
    -0.07
    ovski
    -0.07
    wick
    -0.07
    czyk
    -0.07
    ãĥ¼ãĥĸ
    -0.07
    ÐijÐļ
    -0.07
    æĹłåIJį
    -0.07
    QRST
    -0.07
    POSITIVE LOGITS
     mastery
    0.09
     competency
    0.08
    ä¸ºçĽ®æłĩ
    0.07
     skills
    0.07
     objectives
    0.07
     accomplishment
    0.07
    è¿Ļå°±è¦ģæ±Ĥ
    0.07
     measurable
    0.07
    çŁ¥éģĵèĩªå·±
    0.07
     skill
    0.07
    Activations Density 0.068%

    No Known Activations