© 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. 10942
    Prev
    Next
    INDEX
    Explanations

    comparison values

    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
    vr
    -0.07
    å®ŀåľ¨å¤ª
    -0.07
    èģĶåIJĪä½ĵ
    -0.07
    å¦Ĥæĺ¯
    -0.07
    å¤§åĽĽ
    -0.07
    æĥ³å¾Ĺ
    -0.07
    -Sah
    -0.06
     há»įng
    -0.06
    opup
    -0.06
    对åIJĦ
    -0.06
    POSITIVE LOGITS
     (>
    0.08
    ParameterValue
    0.07
    çĶļèĩ³ä¼ļ
    0.07
    ücks
    0.07
     بÙĥØ«ÙĬر
    0.07
    >[]
    0.07
    çĶļèĩ³
    0.07
     unity
    0.07
    ä¸Ķä¸į
    0.07
    æŃ£å¸¸
    0.06
    Activations Density 0.012%

    No Known Activations