© 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. 9544
    Prev
    Next
    INDEX
    Explanations

    applying operations running opened sea query

    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
    çĽijçĿ£æ£ĢæŁ¥
    -0.12
    æŁ¥çľĭæĽ´å¤ļ
    -0.11
    åĬłå¿«å»ºè®¾
    -0.10
    åģļä¸ĢäºĽ
    -0.10
    ä¹Ĵä¹ĵçIJĥ
    -0.09
    è§Ĥèµı
    -0.09
    ä¿¡æģ¯åıijå¸ĥ
    -0.09
    æ´Ĺæīĭ
    -0.09
    å¤§åĽ½
    -0.09
    人æĢ§åĮĸ
    -0.09
    POSITIVE LOGITS
    -ready
    0.12
    ä¸įäºĨ
    0.10
    -worthy
    0.09
    able
    0.09
     Ready
    0.09
    ableObject
    0.09
     Bik
    0.09
    èĥ½åĬĽå¼º
    0.09
     Greenwood
    0.09
    Ready
    0.08
    Activations Density 1.487%

    No Known Activations