© 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. 51997
    Prev
    Next
    INDEX
    Explanations

    refreshing

    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
    è¢į
    -0.10
    ripple
    -0.09
    NST
    -0.09
    顶å°ĸ
    -0.09
    ç
    -0.09
     explan
    -0.09
    è½®å»ĵ
    -0.08
     Imports
    -0.08
    HIP
    -0.08
     اÙĦرØŃ
    -0.08
    POSITIVE LOGITS
    æ¸ħæĸ°
    0.12
     refreshing
    0.11
    æ¸ħçĪ½
    0.11
    解èĦ±
    0.10
     refresh
    0.10
    ä¹ĭ举
    0.10
    æ¸ħ
    0.09
    å¹²åĩĢ
    0.09
    æ¸ħåĩī
    0.09
    涤
    0.08
    Activations Density 0.013%

    No Known Activations