© 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. 6262
    Prev
    Next
    INDEX
    Explanations

    verb endings

    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
     follando
    -0.11
    éĢīæĭ
    -0.09
    æ¹ĺæ½Ń
    -0.09
    Descripcion
    -0.08
    æį®è¯´
    -0.08
     inher
    -0.08
    ä½ĵä¼ļåĪ°
    -0.08
    respuesta
    -0.08
     nuest
    -0.08
    arrera
    -0.08
    POSITIVE LOGITS
    idade
    0.10
    ipsis
    0.10
    ç¡®
    0.09
    ças
    0.09
    .uf
    0.09
     frankfurt
    0.08
     Alexandre
    0.08
    вл
    0.08
    agens
    0.08
     do
    0.08
    Activations Density 0.164%

    No Known Activations