© 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. 14062
    Prev
    Next
    INDEX
    Explanations

    to connected with for by

    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
    åĥķ
    -0.07
    ewel
    -0.06
    åĬłå¼ºåŃ¦ä¹ł
    -0.06
     cual
    -0.06
    hton
    -0.06
    جÙĬØ©
    -0.06
    hui
    -0.06
     Spre
    -0.06
    å¸Ĥåľºåıijå±ķ
    -0.06
    ़
    -0.06
    POSITIVE LOGITS
    äºİ
    0.09
    æĻĵ彤
    0.08
    indah
    0.07
    ÐŁÐ¾Ð´ÑĢобнее
    0.07
    梧
    0.07
    bling
    0.07
    ä»İåı¥
    0.07
    enko
    0.06
    orting
    0.06
    ofil
    0.06
    Activations Density 0.134%

    No Known Activations