© 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. 32559
    Prev
    Next
    INDEX
    Explanations

    vision and foresight

    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¤ļç§įå½¢å¼ı
    -0.09
    éļ¶å±ŀ
    -0.09
     Lazy
    -0.09
    éĿ³
    -0.09
    好è¿IJ
    -0.09
    Sys
    -0.08
    perf
    -0.08
    å¬
    -0.08
     Little
    -0.08
    é²ľèĬ±
    -0.08
    POSITIVE LOGITS
    éķ¿è¿ľ
    0.17
    çľ¼åħī
    0.16
    çļĦçľ¼åħī
    0.15
    缮åħī
    0.14
     vision
    0.13
    çĿĢçľ¼äºİ
    0.13
    çļĦ缮åħī
    0.13
     fores
    0.12
     shorts
    0.12
    åīįçŀ»æĢ§
    0.12
    Activations Density 0.037%

    No Known Activations