© 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. 51167
    Prev
    Next
    INDEX
    Explanations

    fellow people, senior figures, whom artists

    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
    ä¸İä¼Ĺ
    -0.07
    ancier
    -0.07
    女人
    -0.06
     اÙĦÙĥبرÙī
    -0.06
    主人çļĦ
    -0.06
    rum
    -0.06
    å§IJ夫
    -0.06
    ارÙĬØ©
    -0.06
    é£ŀåİ»
    -0.06
    urma
    -0.06
    POSITIVE LOGITS
    æľĪä¸Ń
    0.08
    ColumnInfo
    0.08
    usher
    0.08
    æľīèĥ½åĬĽ
    0.08
    ä¼ĺç§ĢçļĦ
    0.08
    हत
    0.07
    ivel
    0.07
    æĪĸå¤ļ
    0.07
    phalt
    0.07
    quam
    0.07
    Activations Density 0.356%

    No Known Activations