© 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. 20648
    Prev
    Next
    INDEX
    Explanations

    surveillance cameras and lighting

    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
    ä¸įä»ħè¦ģ
    -0.10
    åĨ³å®ļäºĨ
    -0.09
     spo
    -0.08
    æŁIJ个
    -0.08
    è´¥
    -0.08
    ายà¸Ļ
    -0.08
    å¿į
    -0.08
    è·¯ä¸Ĭ
    -0.08
    å¼Ħ
    -0.08
    åIJİæĤĶ
    -0.08
    POSITIVE LOGITS
    示èĮĥåĮº
    0.11
    产ä¸ļåıijå±ķ
    0.10
    èħ®
    0.10
    wo
    0.10
    管çIJĨåĬŀæ³ķ
    0.09
    çŃīå½¢å¼ı
    0.09
    åŁİåĮº
    0.09
    æī¶æĮģ
    0.08
     miá»ħn
    0.08
     Caul
    0.08
    Activations Density 0.141%

    No Known Activations