© 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. 58647
    Prev
    Next
    INDEX
    Explanations

    diving and scuba equipment

    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
    河边
    -0.09
     Cle
    -0.09
    æĥ©
    -0.09
    antic
    -0.09
    æ´¥
    -0.09
    æ»ĭ润
    -0.09
     anticip
    -0.09
    mium
    -0.09
    åĬ±
    -0.09
    POSITIVE LOGITS
    æ½ľæ°´
    0.17
    æµ·åºķ
    0.11
     diving
    0.11
     underwater
    0.10
    èĩªèIJ¥
    0.10
    深度
    0.10
    ä¸ľæµ·
    0.10
    æ½ľ
    0.09
    æĶĢ
    0.09
    è¶Ł
    0.09
    Activations Density 0.055%

    No Known Activations