© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49283
    Prev
    Next
    INDEX
    Explanations

    place names and surnames

    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
    stro
    -0.09
    çīĮåŃIJ
    -0.09
    Ľ
    -0.09
    åĨ·åĨ»
    -0.09
    è®Ń
    -0.09
    imony
    -0.08
    æŀķ头
    -0.08
     наÑĢ
    -0.08
    ual
    -0.08
    æ»ĵ
    -0.08
    POSITIVE LOGITS
     Fatal
    0.10
    æł·çļĦ
    0.09
    er
    0.09
    ertest
    0.08
    ä¸įçĪ±
    0.08
    rod
    0.08
    rag
    0.08
    estate
    0.08
    ÙħاÙĨ
    0.08
    æİ¥åIJ¬
    0.08
    Activations Density 0.006%

    No Known Activations