© 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. 17279
    Prev
    Next
    INDEX
    Explanations

    increase in throughput, shelf life, quality, density, speed

    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
    åŃ¦è´¹
    -0.10
    esity
    -0.09
    UGHT
    -0.09
    ipse
    -0.09
    cock
    -0.09
    表达äºĨ
    -0.09
    è¾ĥå·®
    -0.09
     повÑĭÑĪен
    -0.09
    dbuf
    -0.09
    Ñģка
    -0.09
    POSITIVE LOGITS
    å·¥ä½ľæķĪçİĩ
    0.10
    çľĭå¾Ĺ
    0.09
    解æĶ¾
    0.09
    æĶ¶çĽĬ
    0.09
    ç»ıæµİæķĪçĽĬ
    0.09
    odge
    0.08
    æ´²
    0.08
     peace
    0.08
    æĢ§ä»·æ¯Ķ
    0.08
    ader
    0.08
    Activations Density 0.307%

    No Known Activations