© 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. 62685
    Prev
    Next
    INDEX
    Explanations

    household or workplace

    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
    åľ¨åģļ好
    -0.08
    stech
    -0.08
    ieni
    -0.08
    .snapshot
    -0.07
    nesty
    -0.07
    ÏĢλα
    -0.07
    drs
    -0.07
    è°
    -0.07
    spath
    -0.07
     Norton
    -0.07
    POSITIVE LOGITS
    家åºŃåĴĮ
    0.08
    家åºŃ
    0.08
     workplaces
    0.08
    ä½ĵèĤ²èµĽäºĭ
    0.08
     workplace
    0.08
    åĴĮ家åºŃ
    0.08
    åķĨä¸ļ
    0.08
    ä½ĵèĤ²
    0.08
    å·¥ä½ľæĪĸ
    0.08
     household
    0.08
    Activations Density 1.562%

    No Known Activations