© 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. 8407
    Prev
    Next
    INDEX
    Explanations

    family-owned businesses

    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
    è¯Ŀåī§
    -0.09
    æ²Ł
    -0.09
    æı´
    -0.09
    év
    -0.09
    æľįåĬ¡å¹³åı°
    -0.09
    磫
    -0.08
     Kia
    -0.08
    å®ĺ
    -0.08
    ç¾İ女
    -0.08
    åħħåĪĨ
    -0.08
    POSITIVE LOGITS
    家æĹı
    0.17
    ç¶ĵçĩŁ
    0.16
    ä¸ī代
    0.15
    ç»ıèIJ¥
    0.15
     Ñģемей
    0.15
    äºĮ代
    0.14
    第ä¸ī代
    0.14
    ä¼łæī¿
    0.13
    ç»ıèIJ¥ç®¡çIJĨ
    0.13
    ä¸ĭä¸Ģ代
    0.13
    Activations Density 0.133%

    No Known Activations