© 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. 57023
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical 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
    bour
    -0.08
    thon
    -0.08
    etten
    -0.08
    wit
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    anol
    -0.07
    .icons
    -0.07
    Contained
    -0.07
    RYPTO
    -0.07
    urado
    -0.07
    POSITIVE LOGITS
     supra
    0.07
    entifier
    0.07
    udge
    0.06
    西æŀĹ
    0.06
    .ta
    0.06
    ardini
    0.06
    ä¸Ĭä¸ĭçıŃ
    0.06
    .newInstance
    0.06
    åĴĮè°IJåıijå±ķ
    0.06
     Jard
    0.06
    Activations Density 0.001%

    No Known Activations