© 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. 63977
    Prev
    Next
    INDEX
    Explanations

    award-winning

    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
    çĿĽ
    -0.09
     поб
    -0.09
    cco
    -0.09
     Indexed
    -0.09
    å¾Ģä¸Ĭ
    -0.09
    omon
    -0.09
    ä¸įè¦ģ太
    -0.08
    .bootstrapcdn
    -0.08
    prises
    -0.08
    ally
    -0.08
    POSITIVE LOGITS
    able
    0.10
    -winning
    0.10
    shire
    0.09
    åħį责声æĺİ
    0.09
    itos
    0.09
    æ¿ł
    0.09
    ë°Ľ
    0.08
    ULL
    0.08
    ingly
    0.08
    æİĸ
    0.08
    Activations Density 0.030%

    No Known Activations