© 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. 47960
    Prev
    Next
    INDEX
    Explanations

    K plus company names

    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
    oron
    -0.10
    åħ·æľīèī¯å¥½
    -0.09
    äºĶæĺŁ
    -0.09
    AGON
    -0.09
    8
    -0.08
    æ¦ľ
    -0.08
    kah
    -0.08
    5
    -0.08
    lus
    -0.08
    å½ĵä¹ĭ
    -0.08
    POSITIVE LOGITS
    ality
    0.09
    (K
    0.09
    awai
    0.09
    æ°ijèIJ¥ç»ıæµİ
    0.09
    窿
    0.08
    wie
    0.08
    太å¤ļçļĦ
    0.08
    лоÑĤ
    0.08
    abouts
    0.08
    èķī
    0.08
    Activations Density 0.412%

    No Known Activations