© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56829
    Prev
    Next
    INDEX
    Explanations

    speaks for itself or directly

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æİ¥
    -0.10
    æŃ£æĺ¯
    -0.09
    orrent
    -0.09
    habit
    -0.09
    xic
    -0.09
    Æ°á»Łng
    -0.08
    .Apis
    -0.08
    .vo
    -0.08
    /os
    -0.08
    assi
    -0.08
    POSITIVE LOGITS
    å·¥åºı
    0.10
    è¿ĩåİ»çļĦ
    0.09
    åĮł
    0.09
    è¯Ŀ说
    0.09
    æĦ
    0.08
    æ®ĸæ°ij
    0.08
    edm
    0.08
    磾
    0.08
     headlines
    0.08
    ota
    0.08
    Activations Density 0.010%

    No Known Activations