© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29555
    Prev
    Next
    INDEX
    Explanations

    electricity grid and network

    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
    Negative Logits
    éĺµ
    -0.10
    æĭ¿
    -0.09
    hare
    -0.09
    家éĩĮ
    -0.09
    hip
    -0.09
    åĴĭ
    -0.08
     Wich
    -0.08
     Stam
    -0.08
    cretion
    -0.08
    ä¿Ŀ管
    -0.08
    POSITIVE LOGITS
    转弯
    0.10
    ä½ĵç³»
    0.10
    æĸ°è¥¿
    0.10
    åĽ½å®¶çº§
    0.09
    åIJģ
    0.09
    åĬłæĭ¿
    0.09
    æĢ»å±Ģ
    0.09
    çĵ¦
    0.09
     bust
    0.09
    usters
    0.09
    Activations Density 0.041%

    No Known Activations