© 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. 37316
    Prev
    Next
    INDEX
    Explanations

    proper nouns or conjunctions

    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
    2
    -0.10
    çľĭä¸Ģçľĭ
    -0.09
    4
    -0.09
    5
    -0.09
    1
    -0.09
    8
    -0.09
    9
    -0.09
    0
    -0.09
    3
    -0.08
    6
    -0.08
    POSITIVE LOGITS
    èĢĮçİ°åľ¨
    0.23
    åĪ°çİ°åľ¨
    0.21
    ä½Ĩçİ°åľ¨
    0.20
    å¦Ĥä»Ĭ
    0.18
    åIJİæĿ¥
    0.17
    çİ°åľ¨å·²ç»ı
    0.16
    èĩ³ä»Ĭ
    0.16
    æѤåIJİ
    0.14
    ä»Ĭãģ¯
    0.14
    å¾Įä¾Ĩ
    0.14
    Activations Density 0.217%

    No Known Activations