© 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. 61416
    Prev
    Next
    INDEX
    Explanations

    objects or common things

    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
    strt
    -0.09
    æĮīæŶ
    -0.09
    å¥ĩå¼Ĥ
    -0.08
     дÑĥÑħ
    -0.08
     Kash
    -0.08
    æ´»
    -0.08
    Ñģо
    -0.08
    lev
    -0.08
    åľŃ
    -0.08
    gesch
    -0.08
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.10
    ä¼¼çļĦ
    0.10
    æĸĹ
    0.09
    åİĨåı²æĸ°
    0.09
     Bourbon
    0.09
    èĬ®
    0.09
    éĤ£ä¸ĢåĪ»
    0.09
    以èĩ³äºİ
    0.08
    ç»Īæŀģ
    0.08
    以åħ¶
    0.08
    Activations Density 0.095%

    No Known Activations