© 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. 51842
    Prev
    Next
    INDEX
    Explanations

    positive comparisons or contrasts

    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
    egan
    -0.09
    uch
    -0.09
    äºĮ代
    -0.09
    è¿Ļä¹Īå¤ļ
    -0.08
    éĤ£ä¹Īå¤ļ
    -0.08
    acle
    -0.08
    æĽ¿ä»£
    -0.08
    æĨ©
    -0.08
    UCH
    -0.08
    å®ļåIJij
    -0.08
    POSITIVE LOGITS
    ä¸İåIJ¦
    0.27
     or
    0.19
     vs
    0.17
     versus
    0.16
     или
    0.15
    æĪĸ
    0.15
    ãģ¾ãģŁãģ¯
    0.13
     íĺ¹ìĿĢ
    0.13
    ê±°ëĤĺ
    0.13
     ÙĪغÙĬر
    0.12
    Activations Density 0.543%

    No Known Activations