© 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. 8534
    Prev
    Next
    INDEX
    Explanations

    think tank

    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¡ĮæĶ¿å®¡æī¹
    -0.09
     اÙĦÙĪاØŃد
    -0.09
    åĬŀåħ¬
    -0.09
    hip
    -0.09
    hips
    -0.08
     ngá»Ļ
    -0.08
    åľ¨èģĮ
    -0.08
     WTF
    -0.08
     Nep
    -0.08
    å·¥ç¨ĭæľºæ¢°
    -0.08
    POSITIVE LOGITS
    åħ¬åı¸çļĦ
    0.11
    çķĮçļĦ
    0.10
    ä¼ģä¸ļçļĦ
    0.09
    大çĪ·
    0.09
    èĢħçļĦ
    0.09
    çķĮ
    0.09
    è´µ
    0.09
    æ°ijåĬŀ
    0.09
    寡
    0.09
    巨头
    0.09
    Activations Density 0.106%

    No Known Activations