© 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. 12349
    Prev
    Next
    INDEX
    Explanations

    input/output operations

    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
    ween
    -0.11
    çĶŁæ´»è´¨éĩı
    -0.10
    neath
    -0.10
    ëī´ìĬ¤
    -0.09
    /filepath
    -0.09
    iff
    -0.09
    å¦ŀ
    -0.09
    ä¹Łä¸įæĥ³
    -0.09
    uer
    -0.09
    åıįè¿ĩæĿ¥
    -0.09
    POSITIVE LOGITS
    .IOException
    0.09
    athon
    0.09
    èĩªåľ¨
    0.09
    ILI
    0.09
    åijĬ
    0.09
    ickey
    0.08
     Barnett
    0.08
    yers
    0.08
    .FileNotFoundException
    0.08
    nar
    0.08
    Activations Density 0.085%

    No Known Activations