© 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. 40277
    Prev
    Next
    INDEX
    Explanations

    team and sports affiliation

    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
    .rad
    -0.09
    åįļæĸĩ
    -0.08
    å¨ģæħij
    -0.08
     dere
    -0.08
    æºħ
    -0.08
    rd
    -0.08
    éĢį
    -0.08
    æľīçĶ¨çļĦ
    -0.07
    建åĨĽ
    -0.07
    etry
    -0.07
    POSITIVE LOGITS
     беÑģплаÑĤно
    0.11
    è¾ĵäºĨ
    0.10
    æĪIJè´¥
    0.10
     allegiance
    0.10
    vos
    0.09
    CRY
    0.09
    onte
    0.09
    èĥľè´Ł
    0.09
    _BROWSER
    0.09
    okus
    0.09
    Activations Density 0.014%

    No Known Activations