© 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. 60874
    Prev
    Next
    INDEX
    Explanations

    numbers and code

    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
    æĥ³ä¸įåĪ°
    -0.07
    atul
    -0.07
    å½ĵåīįä½įç½®
    -0.07
    iper
    -0.07
    ربÙĩ
    -0.07
    ander
    -0.07
    anko
    -0.07
    ebra
    -0.07
     %#
    -0.07
    ä¿ł
    -0.07
    POSITIVE LOGITS
    åĸĢ
    0.07
    OUCH
    0.07
     inc
    0.07
    驻马
    0.06
    ãĥŁãĥİ
    0.06
    ordio
    0.06
     aw
    0.06
    ptico
    0.06
    åĬ¨
    0.06
    espo
    0.06
    Activations Density 0.114%

    No Known Activations