© 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. 19595
    Prev
    Next
    INDEX
    Explanations

    first

    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
     presunto
    -0.08
    çļĦç¾İ女
    -0.08
    微信æī«ä¸Ģæī«
    -0.07
    彪
    -0.07
     factura
    -0.07
     اÛĮÙĨÚ©Ùĩ
    -0.07
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    -0.07
    åĴĮ帮åĬ©
    -0.06
    prompt
    -0.06
    å°½äºĨ
    -0.06
    POSITIVE LOGITS
     choice
    0.09
    å°ıéģĵ
    0.08
    eno
    0.07
    choice
    0.07
    _VOLUME
    0.07
    "title
    0.07
    åĵģ
    0.07
    atra
    0.07
    geries
    0.07
    æĥħæľī
    0.07
    Activations Density 0.452%

    No Known Activations