© 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. 51490
    Prev
    Next
    INDEX
    Explanations

    even added

    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
     either
    -0.12
     nevertheless
    -0.12
    ãģ¨ãģ«ãģĭãģı
    -0.11
    æĹłè®ºå¦Ĥä½ķ
    -0.11
    è¦ģä¹Ī
    -0.10
     nonetheless
    -0.10
    åį³åı¯
    -0.09
     forever
    -0.09
     ÑĤакже
    -0.09
     also
    -0.09
    POSITIVE LOGITS
    æľīæŶåĢĻ
    0.12
    åı¯ä»¥è¯´æĺ¯
    0.11
    æľīæīĢ
    0.11
    å°±è¿ŀ
    0.11
    ä¸Ģ度
    0.10
    -handed
    0.10
    æľīæŶ
    0.10
    æŁIJç§įç¨ĭ度
    0.10
    ä¸įæĥľ
    0.10
     sometimes
    0.10
    Activations Density 0.057%

    No Known Activations