© 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. 52224
    Prev
    Next
    INDEX
    Explanations

    making decisions or choices

    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
    åĨ³å¿ĥ
    -0.10
    模çī¹
    -0.09
    æ¹ľ
    -0.08
     Resolution
    -0.08
    lash
    -0.08
    ä½łèĩªå·±
    -0.08
    å¸Ĥåľºç»ıæµİ
    -0.08
    _resolution
    -0.08
    æĹłç©·
    -0.08
    æ§
    -0.08
    POSITIVE LOGITS
     about
    0.09
    éĹľæĸ¼
    0.09
     Pry
    0.09
    ä¸įè§ģ
    0.08
    åħ³äºİ
    0.08
    ä¸įäºĨ
    0.08
     Bout
    0.08
    举æĬ¥çĶµè¯Ŀ
    0.08
     tentang
    0.08
    -about
    0.08
    Activations Density 0.030%

    No Known Activations