© 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. 50862
    Prev
    Next
    INDEX
    Explanations

    source said told

    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
    笤
    -0.07
    fér
    -0.07
    unct
    -0.07
    åľŁèĢ³
    -0.07
    igs
    -0.07
    ContentLoaded
    -0.06
    ×Ļרת
    -0.06
    FER
    -0.06
    çĽĨ
    -0.06
    ×ŀ×ķש
    -0.06
    POSITIVE LOGITS
    æŁIJ个
    0.09
    æŁIJ
    0.09
     presumably
    0.08
    æŁIJçļĦ
    0.08
    æŁIJç§į
    0.08
     apparently
    0.07
    æŁIJæŁIJ
    0.07
    æŁIJ人
    0.07
    è¿Ļä¹Ī说
    0.07
     probable
    0.07
    Activations Density 0.021%

    No Known Activations