© 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. 6179
    Prev
    Next
    INDEX
    Explanations

    open mind, attitude, patience, willingness

    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
    csr
    -0.11
    avis
    -0.09
    åĪ¶
    -0.09
     Kent
    -0.08
    æľī害
    -0.08
     Cho
    -0.08
    inux
    -0.08
    arent
    -0.08
    atti
    -0.07
    gle
    -0.07
    POSITIVE LOGITS
    çľĭå¾ħ
    0.11
    æĬ±çĿĢ
    0.10
    æĤ¨çļĦåŃ©åŃIJ
    0.10
    çļĦ带é¢Ĩ
    0.10
    æħĭ
    0.10
    æĢĢéĩĮ
    0.09
    çļĦå¿ĥæĢģ
    0.09
    çļĦåīįæıIJä¸ĭ
    0.09
    .kotlin
    0.09
    /rfc
    0.09
    Activations Density 0.019%

    No Known Activations