© 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. 12345
    Prev
    Next
    INDEX
    Explanations

    visit to a house

    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
    ailer
    -0.11
     MO
    -0.09
    æŃ¤é¡¹
    -0.09
    æľ¬å±Ĭ
    -0.08
    éĢ¢
    -0.08
    chia
    -0.08
    cry
    -0.08
     lame
    -0.08
    chio
    -0.08
    åįĥéĩĮ
    -0.08
    POSITIVE LOGITS
    çļĦæĹ¥åŃIJ
    0.11
    _dur
    0.10
    æĮĩçĤ¹
    0.10
    æĮŁ
    0.10
    usz
    0.09
    dur
    0.09
    ocop
    0.09
    åĪĽæĸ°èĥ½åĬĽ
    0.09
    NDER
    0.09
    æĪijæĬĬ
    0.09
    Activations Density 0.018%

    No Known Activations