© 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. 59182
    Prev
    Next
    INDEX
    Explanations

    towel and towels

    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
    fills
    -0.10
    thur
    -0.10
    æĺŃ
    -0.09
    åĿļåĽº
    -0.09
    @student
    -0.09
    çļ®éĿ©
    -0.09
    éľĩæĴ¼
    -0.09
    éŀ£
    -0.09
    éľĩæĥĬ
    -0.09
    ulet
    -0.09
    POSITIVE LOGITS
     towel
    0.11
     tiles
    0.09
    æ¯Ľå·¾
    0.09
     hosp
    0.09
     towels
    0.09
     sponge
    0.08
    åŃĺ
    0.08
    lon
    0.08
    .ServiceModel
    0.08
    _tiles
    0.08
    Activations Density 0.032%

    No Known Activations