© 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. 52205
    Prev
    Next
    INDEX
    Explanations

    different or various types

    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
    íķĢ
    -0.10
    æİ¥éĢģ
    -0.09
    çĥĺ
    -0.09
    _ANT
    -0.09
    ikan
    -0.09
    èĩªæĿ¥æ°´
    -0.09
    GRAM
    -0.09
    orous
    -0.09
    梦è§ģ
    -0.09
    bell
    -0.09
    POSITIVE LOGITS
    泡
    0.08
    æĸ¹éĿ¢
    0.08
     different
    0.08
    ç±»åŀĭçļĦ
    0.08
    strand
    0.08
    ä¸įåIJĮçļĦ
    0.07
    æĭĽ
    0.07
    éĺ¶æ®µ
    0.07
     Marks
    0.07
    æľį
    0.07
    Activations Density 0.039%

    No Known Activations