© 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. 8626
    Prev
    Next
    INDEX
    Explanations

    usr/bin/env python

    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
    yster
    -0.09
    çī¢åĽº
    -0.09
    æ¯Ĵç´ł
    -0.09
    ä½ľèĢħæľ¬äºº
    -0.08
    åĩ¹
    -0.08
    åµĩ
    -0.08
    åįļçī©
    -0.08
    æ·«
    -0.08
    prot
    -0.08
    æĸ°è¥¿
    -0.08
    POSITIVE LOGITS
    cen
    0.08
    庾
    0.08
    íķı
    0.08
    asy
    0.08
    åĩĨ
    0.08
     ass
    0.08
    assen
    0.08
    anj
    0.08
    ç»ĺåĪ¶
    0.08
    ä¸įåı¯
    0.08
    Activations Density 0.001%

    No Known Activations