© 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. 12267
    Prev
    Next
    INDEX
    Explanations

    O(n) notation

    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
    (si
    -0.08
    对äºİä¸ĢäºĽ
    -0.07
    æĺ¯å±ŀäºİ
    -0.07
    NameValuePair
    -0.07
    leftright
    -0.06
    .xhtml
    -0.06
    ä¸įæŶ
    -0.06
    :hidden
    -0.06
    ControlItem
    -0.06
     usual
    -0.06
    POSITIVE LOGITS
     ÑıкобÑĭ
    0.08
     Ryder
    0.08
    并æıIJåĩº
    0.07
    iter
    0.07
     vs
    0.07
    statt
    0.07
     müsse
    0.07
    è¦ģ强åĮĸ
    0.07
    atak
    0.07
    legen
    0.07
    Activations Density 0.002%

    No Known Activations