© 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. 8162
    Prev
    Next
    INDEX
    Explanations

    communitarianism, education, ethics, friendship, distance

    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
    ä¸įæŃ¢
    -0.09
    æű
    -0.09
    èµ°è¿ĩ
    -0.09
    çİ°çĬ¶
    -0.09
    强硬
    -0.08
    é¸Ń
    -0.08
    ä¸įåŃĺåľ¨
    -0.08
    æĬ¢åįł
    -0.08
    æīĵçł´äºĨ
    -0.08
    ä»Ĭ天çļĦ
    -0.08
    POSITIVE LOGITS
    è¡¡
    0.10
    宪
    0.10
    åĴ»
    0.10
    ç¾İå¾·
    0.09
     virtue
    0.09
    -fly
    0.09
    æĿ¥åĽŀ
    0.09
    èIJ¥åĪ©
    0.09
    å»·
    0.09
    修身
    0.09
    Activations Density 0.103%

    No Known Activations