© 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. 747
    Prev
    Next
    INDEX
    Explanations

    used to

    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
    ä¸ĩä¸Ģ
    -0.09
    å¹³åı°ä¸Ĭ
    -0.08
    .delay
    -0.08
    诸å¦Ĥ
    -0.08
    æĪijä¸į
    -0.08
    çĿ£
    -0.08
    åĸĩåıŃ
    -0.08
    åħ¶æīĢ
    -0.08
    tees
    -0.08
    鬼
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.12
    ly
    0.12
    æľīä¸Ģç§į
    0.12
    æĿ¥è¯´
    0.10
    æĺ¯ä¸Ģä½į
    0.10
     Yap
    0.09
    饽
    0.09
    arti
    0.09
    çıº
    0.09
    éķ³
    0.09
    Activations Density 0.034%

    No Known Activations