© 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. 52274
    Prev
    Next
    INDEX
    Explanations

    street names and locations

    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
    ÑİÑĢ
    -0.09
    akah
    -0.09
    æºIJæºIJ
    -0.09
    adin
    -0.09
    ulp
    -0.09
    Saga
    -0.09
    å¨ł
    -0.09
    æŀģ大
    -0.09
    åĭº
    -0.09
    .LA
    -0.08
    POSITIVE LOGITS
    åIJ¬åIJ¬
    0.10
    è¯
    0.09
    ä¿Ł
    0.09
    ä¹īåĬ¡æķĻèĤ²
    0.08
     classNames
    0.08
    çļĦèĦļæŃ¥
    0.08
    olated
    0.08
    æĮīæŶ
    0.08
    idor
    0.08
    à¦Ļ
    0.08
    Activations Density 0.002%

    No Known Activations