© 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. 31401
    Prev
    Next
    INDEX
    Explanations

    iOS, browser, Apple policies

    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
    andong
    -0.08
    andle
    -0.08
    ellig
    -0.08
    ÙħاÛĮ
    -0.07
    .opensource
    -0.07
    åıĬå®īåħ¨
    -0.07
    illet
    -0.07
    è¿ĩç¨ĭå½ĵä¸Ń
    -0.07
    åľ¨è¿Ļ个è¿ĩç¨ĭä¸Ń
    -0.07
    .pixel
    -0.07
    POSITIVE LOGITS
    ä¹Łæĺ¯
    0.08
    akin
    0.08
    æļ´é£İ
    0.08
    ä¹Łæĺ¯ä¸Ģ
    0.08
    aptic
    0.07
    ä¹ŁæĪIJäºĨ
    0.07
    avy
    0.07
    yla
    0.07
    ::$_
    0.07
    æĥħçļĦ
    0.07
    Activations Density 0.114%

    No Known Activations