© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18782
    Prev
    Next
    INDEX
    Explanations

    ethnic origins and cultures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unknown
    -0.05
     dens
    -0.05
    çľĭä¸į
    -0.05
    –
    -0.05
     cero
    -0.05
     visit
    -0.05
     dense
    -0.04
    вени
    -0.04
     they
    -0.04
     presented
    -0.04
    POSITIVE LOGITS
    доб
    0.07
    ibri
    0.06
    åĶ¤
    0.06
    iculo
    0.06
    æł¼å¤ĸ
    0.06
    大åħ¬
    0.06
    insn
    0.06
     Doutor
    0.06
    ÛĮدÛĮ
    0.06
     Nug
    0.06
    Activations Density 0.017%

    No Known Activations