© 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. 20429
    Prev
    Next
    INDEX
    Explanations

    Salmonella enterica serovar

    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
    æģ¶æĦı
    -0.13
    è¢ĭåŃIJ
    -0.10
    ä¸įèĥ½åĨį
    -0.10
    æµ·åħ³
    -0.10
    ungs
    -0.10
    elts
    -0.10
    ashes
    -0.10
    èĩªçĶ±è´¸æĺĵ
    -0.09
    ä¸ŃåĽ½æĶ¿åºľ
    -0.09
    å½ĵä¹ĭ
    -0.09
    POSITIVE LOGITS
    cher
    0.08
    è£
    0.08
    ullen
    0.08
    tones
    0.08
    失
    0.07
    åİ¥
    0.07
     special
    0.07
     оÑģоб
    0.07
    uch
    0.07
    å¬ĸ
    0.07
    Activations Density 0.146%

    No Known Activations