© 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. 20614
    Prev
    Next
    INDEX
    Explanations

    breakthrough and advances

    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
    é©·
    -0.09
    ä¼łéĢĴ
    -0.09
    å¤įå·¥å¤į产
    -0.09
    å°±æĺ¯è¦ģ
    -0.09
    ä¾µèļĢ
    -0.08
    ä¹ĭæĥħ
    -0.08
    è¶ħæłĩ
    -0.08
    ä¼łæī¿
    -0.08
    çĪ¬
    -0.08
    ftime
    -0.08
    POSITIVE LOGITS
    çªģçł´
    0.23
     breakthrough
    0.18
    éĩĮç¨ĭç¢ij
    0.15
    çªģçł´åı£
    0.14
    æīĵçł´
    0.14
    é£ŀè·ĥ
    0.13
    çļĦéĩį大
    0.13
    è¿Īåĩº
    0.13
    è¿ĽæŃ¥
    0.12
    çļĦè¿ĽæŃ¥
    0.12
    Activations Density 0.095%

    No Known Activations