© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 30845
    Prev
    Next
    INDEX
    Explanations

    boats and sailing

    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
    å´Ľ
    -0.10
    æİĤ
    -0.10
    ä½łåĸľæ¬¢
    -0.10
    éĵĽ
    -0.10
    帮
    -0.09
    udo
    -0.09
    ç»į
    -0.09
    åĪ¸
    -0.08
    æĺ¯å¤ļä¹Ī
    -0.08
    æľīå¤ļä¹Ī
    -0.08
    POSITIVE LOGITS
     اÙĦشر
    0.10
    ikal
    0.09
    åĮ¼
    0.08
    ÙĬات
    0.08
    éo
    0.08
    ICAL
    0.08
    .EventQueue
    0.08
    äºĮæīĭ
    0.08
    ignum
    0.08
     Locker
    0.08
    Activations Density 0.028%

    No Known Activations