© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21005
    Prev
    Next
    INDEX
    Explanations

    Syrian Civil War related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ermen
    -0.10
    edException
    -0.10
    æł¡åĮº
    -0.09
    æĥħ趣
    -0.09
    æľįåĬ¡åĮº
    -0.09
    ness
    -0.09
     trì
    -0.09
    vier
    -0.09
    manship
    -0.09
    sgi
    -0.08
    POSITIVE LOGITS
     ÙĪاÙĦع
    0.09
    好è¿IJ
    0.09
    纶
    0.09
     اÙĦÙħسÙĦØŃØ©
    0.08
    abama
    0.08
    ullah
    0.08
    deo
    0.08
    ouro
    0.08
    icate
    0.08
     اÙĦÙħستÙĤبÙĦ
    0.08
    Activations Density 0.006%

    No Known Activations