© 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. 20909
    Prev
    Next
    INDEX
    Explanations

    while + action

    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
    å¹ķ
    -0.12
     зÑĢ
    -0.09
    ä¹ĭæīĢ
    -0.09
    ä¸įè¦ģ太
    -0.08
     Curtain
    -0.08
     Dayton
    -0.08
    åħħåĪĨåĪ©çĶ¨
    -0.08
    çļĦçĶŁæ´»
    -0.08
    uste
    -0.08
    æŃ¤æ¬¡
    -0.08
    POSITIVE LOGITS
    è¯ķåĽ¾
    0.10
     trying
    0.10
    驾é©Ń
    0.09
    çĿ£åĬŀ
    0.09
    éĴ¿
    0.08
    rec
    0.08
    é¢ĦæĬ¥
    0.08
    omin
    0.08
    èĩªå¸¦
    0.08
    ä»įåľ¨
    0.08
    Activations Density 0.044%

    No Known Activations