© 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. 65337
    Prev
    Next
    INDEX
    Explanations

    ethnic groups and comparisons

    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
    wards
    -0.10
    ills
    -0.08
    áĥIJáĥľ
    -0.08
    ắt
    -0.08
    warzys
    -0.07
    çĦ¶æĺ¯
    -0.07
    á»ĭch
    -0.07
    aries
    -0.07
    imal
    -0.07
    aus
    -0.07
    POSITIVE LOGITS
    /gen
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.07
    ciuti
    0.07
    èģĶåIJĪä¼ļ
    0.07
    ayat
    0.07
    /group
    0.07
    /spec
    0.07
    olim
    0.07
    vre
    0.07
    à¹Ĭะ
    0.07
    Activations Density 0.062%

    No Known Activations