© 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. 64644
    Prev
    Next
    INDEX
    Explanations

    African words and related concepts

    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
    зво
    -0.08
    LY
    -0.08
    fully
    -0.08
    полни
    -0.08
    夥
    -0.08
    gar
    -0.08
    براÙĨ
    -0.08
    enance
    -0.07
    arity
    -0.07
    metatable
    -0.07
    POSITIVE LOGITS
    zal
    0.07
    çĮªçĺŁ
    0.07
    jects
    0.07
    ograms
    0.07
    ocos
    0.07
    åIJĮéģĵ
    0.07
    emie
    0.07
    ölcs
    0.07
    thal
    0.07
    ënt
    0.07
    Activations Density 0.045%

    No Known Activations