© 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. 37005
    Prev
    Next
    INDEX
    Explanations

    California, Ontario, University name suffixes

    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
    æį·
    -0.09
     Lotus
    -0.09
    íķij
    -0.08
    å¹»
    -0.08
    bud
    -0.08
    ä¸ĩ家
    -0.08
    éľĦ
    -0.08
    æĮĩæݧ
    -0.08
    CursorPosition
    -0.08
    ewater
    -0.08
    POSITIVE LOGITS
    æ¢ĵ
    0.09
    æľīä»·åĢ¼çļĦ
    0.09
    nder
    0.09
    å¢ŀåĬłåĢ¼
    0.08
    /server
    0.08
    èĵį
    0.08
    Fred
    0.08
     Fab
    0.08
    æĮº
    0.08
    åĩĽ
    0.08
    Activations Density 0.056%

    No Known Activations