© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52763
    Prev
    Next
    INDEX
    Explanations

    speed and performance

    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
    æµģåĬ¨æĢ§
    -0.10
    åľ¨çĶŁæ´»ä¸Ń
    -0.09
    SCO
    -0.09
    åѦåĪ°
    -0.09
    çĶŁæ´»ä¸Ń
    -0.09
    ucz
    -0.09
    æĬķèµĦé¢Ŀ
    -0.08
    客è§Ĥ
    -0.08
    åģľäº§
    -0.08
    å¿ĥ仪çļĦ
    -0.08
    POSITIVE LOGITS
    æķĪçİĩ
    0.15
    éĢŁåº¦
    0.15
    é«ĺæķĪ
    0.13
     performance
    0.13
    æĢ§èĥ½
    0.12
    é«ĺæķĪçļĦ
    0.12
     speed
    0.12
    çļĦéĢŁåº¦
    0.11
     efficiency
    0.11
     CPU
    0.11
    Activations Density 0.471%

    No Known Activations