© 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. 37073
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty or necessity

    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
    æľ¬æĿ¥
    -0.09
    丫
    -0.09
     Granite
    -0.08
    åĭŁ
    -0.08
    _RB
    -0.08
     Dag
    -0.08
    Bang
    -0.08
    çĴŁ
    -0.08
     arguably
    -0.08
    quite
    -0.07
    POSITIVE LOGITS
     surely
    0.14
     Surely
    0.13
    ä¸įèĩ³äºİ
    0.11
     ÐĴедÑĮ
    0.11
    åī¥
    0.11
    好äºĭ
    0.10
    æ¯ķç«Ł
    0.10
    æѤæĸĩ
    0.10
    å°ļ
    0.10
    ä¸įçĦ¶
    0.10
    Activations Density 0.197%

    No Known Activations