© 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. 7766
    Prev
    Next
    INDEX
    Explanations

    for years, time, decades

    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
    åħ¨éĿ¢æİ¨è¿Ľ
    -0.10
    å½ĵæŶçļĦ
    -0.10
    åįĥä¸ĩ
    -0.10
    å½ĵæŶ
    -0.10
    asca
    -0.09
    è¿Ļè¾ĪåŃIJ
    -0.09
    æ¢
    -0.09
    ä»»ä½ķæŶåĢĻ
    -0.09
    åħ¨ç¨ĭ
    -0.09
    ä¸ĢçĶŁ
    -0.09
    POSITIVE LOGITS
    ago
    0.10
    ãģ¶ãĤĬ
    0.10
    çĽ¸ä¼ł
    0.10
    以ä¾Ĩ
    0.10
    ä½İè¿·
    0.10
    以æĿ¥
    0.09
     ago
    0.09
    åĽ°æī°
    0.09
    许ä¹ħ
    0.09
    quito
    0.09
    Activations Density 0.056%

    No Known Activations