© 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. 38779
    Prev
    Next
    INDEX
    Explanations

    companies and indexes

    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
    æ¸Ń
    -0.10
     Garner
    -0.10
     Wax
    -0.09
     Stacy
    -0.09
    èµĺ
    -0.08
    áĢĿ
    -0.08
    anus
    -0.08
    äºĭåĬ¡
    -0.08
    agon
    -0.08
    å·
    -0.08
    POSITIVE LOGITS
    æī§æķĻ
    0.09
    æĶ¶ç´§
    0.09
    atics
    0.09
    忧
    0.08
     Ñģка
    0.08
    ç»Ŀä¸į
    0.08
    cht
    0.08
    raq
    0.08
    полн
    0.08
    空ä¸Ń
    0.08
    Activations Density 0.002%

    No Known Activations