© 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. 20582
    Prev
    Next
    INDEX
    Explanations

    individually oralone or separately

    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
    åħ³æĢĢ
    -0.09
    é«ĺæ¡£
    -0.09
    æľī两个
    -0.08
    åĮ»èį¯
    -0.08
     BRE
    -0.08
    âm
    -0.08
    è¾¹å¢ĥ
    -0.08
    Ùĥسب
    -0.08
    eness
    -0.08
    éĨĴæĿ¥
    -0.08
    POSITIVE LOGITS
    åįķçĭ¬
    0.28
     alone
    0.21
     individually
    0.20
    alone
    0.20
    çĭ¬èĩª
    0.17
     Alone
    0.16
     individual
    0.16
    个ä½ĵ
    0.16
    åĪĨå¼Ģ
    0.16
    åIJĦèĩª
    0.15
    Activations Density 0.144%

    No Known Activations