© 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. 25418
    Prev
    Next
    INDEX
    Explanations

    two following entities

    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
    uccio
    -0.08
    诸
    -0.08
    çļĦè¯Ŀ
    -0.08
    andia
    -0.08
    achi
    -0.07
    æĺ¯ä¸įä¼ļ
    -0.07
    är
    -0.07
    onga
    -0.07
    หà¸Ļึà¹Īà¸ĩ
    -0.07
     solchen
    -0.07
    POSITIVE LOGITS
     aforementioned
    0.13
     respective
    0.09
    -dimensional
    0.08
     main
    0.08
     strongest
    0.08
     simplest
    0.08
     remaining
    0.08
    oretical
    0.08
    itarian
    0.08
     largest
    0.08
    Activations Density 0.052%

    No Known Activations