© 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. 1859
    Prev
    Next
    INDEX
    Explanations

    late periods or years

    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
    кÑģ
    -0.08
    åģļå¾Ĺ
    -0.08
    ibri
    -0.08
    zheimer
    -0.08
    ứt
    -0.08
     Imp
    -0.08
    çĥĻ
    -0.08
    à¸Ĺà¸Ķ
    -0.08
     Zombie
    -0.08
     menn
    -0.08
    POSITIVE LOGITS
    å¿IJ
    0.10
    .matcher
    0.10
    çŁ³å®¶
    0.09
    泡沫
    0.09
    æĸ°æµªå¾®åįļ
    0.09
    çĽĺçĤ¹
    0.08
    æĿµ
    0.08
    é³Ĺ
    0.08
    人次
    0.08
    æµģåIJij
    0.08
    Activations Density 0.095%

    No Known Activations