© 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. 6256
    Prev
    Next
    INDEX
    Explanations

    optical filters and resonators

    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
    èĥ¤
    -0.09
    éľŃ
    -0.09
    æĶĢ
    -0.09
    CHASE
    -0.09
    æºIJæ³ī
    -0.08
    æĿŀ
    -0.08
     Geh
    -0.08
    PIN
    -0.08
    æĺ¥èĬĤæľŁéĹ´
    -0.08
    çĿĢæīĭ
    -0.08
    POSITIVE LOGITS
    滤
    0.10
     filter
    0.10
    åħ±æĮ¯
    0.10
    åı°ä¸Ĭ
    0.09
    ä¸įéĢļ
    0.09
    åĪļ好
    0.09
    filter
    0.09
     filtro
    0.09
    è¿ĩ滤
    0.09
    çľĭéĩį
    0.09
    Activations Density 0.218%

    No Known Activations