© 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. 9210
    Prev
    Next
    INDEX
    Explanations

    holes cut

    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
    骧
    -0.10
    anson
    -0.09
    åŃº
    -0.09
    å·Ŀ
    -0.09
    ä¹±
    -0.09
    çľī头
    -0.09
    åıijçĶŁåıĺåĮĸ
    -0.09
    æ»ļæ»ļ
    -0.08
     available
    -0.08
     established
    -0.08
    POSITIVE LOGITS
     позволÑı
    0.11
    æıIJ
    0.10
    容纳
    0.09
    æģ°
    0.09
    ä¸ĩ人
    0.09
    ijn
    0.09
    oms
    0.08
    æĸ¯åŁº
    0.08
     qed
    0.08
    _INC
    0.08
    Activations Density 0.212%

    No Known Activations