© 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. 4433
    Prev
    Next
    INDEX
    Explanations

    types offiberseedoilglutendairyfishsamplethermalresearchclamshell

    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
     latter
    -0.07
    æĶ
    -0.07
    Õ¿
    -0.07
    ablish
    -0.06
     sag
    -0.06
            č↵        č↵
    -0.06
    ORI
    -0.06
    PIX
    -0.06
    reis
    -0.06
    æŬ
    -0.06
    POSITIVE LOGITS
    asca
    0.08
    åĬ¨åĬ¨
    0.07
    avu
    0.07
    usta
    0.07
     balas
    0.07
    书åŁİ
    0.07
    uwen
    0.07
    etem
    0.07
    etu
    0.07
    åĢ¾åŁİ
    0.07
    Activations Density 0.186%

    No Known Activations