© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 58425
    Prev
    Next
    INDEX
    Explanations

    India IT and industry sector

    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®īåħ¨äºĭæķħ
    -0.10
    blind
    -0.10
    æīŃ
    -0.09
    ToLocal
    -0.09
    å¢ĥå¤ĸ
    -0.09
    ihil
    -0.09
    ä¸ĢåIJį
    -0.09
    åģļ人
    -0.09
    _RS
    -0.09
    çī©ä¸ļ管çIJĨ
    -0.09
    POSITIVE LOGITS
    åζéĢłä¸ļ
    0.11
    产ä¸ļéĽĨ群
    0.10
    产ä¸ļ
    0.10
     industries
    0.09
    æĬĢæľ¯çłĶåıij
    0.09
    ä½łä»¥ä¸º
    0.09
    çϽ天
    0.09
     Manufacturing
    0.09
    org
    0.09
    åįļ主
    0.09
    Activations Density 0.129%

    No Known Activations