© 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. 55795
    Prev
    Next
    INDEX
    Explanations

    wall art and decoration

    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
    è¸ı
    -0.09
    åĨįæĿ¥
    -0.09
     Arb
    -0.09
     ÐłÐµÑģпÑĥб
    -0.09
    æĤ¸
    -0.09
     siblings
    -0.09
    siblings
    -0.08
    stu
    -0.08
    .vocab
    -0.08
     اÙĦرÙĪ
    -0.08
    POSITIVE LOGITS
    å¢Ļä¸Ĭ
    0.12
    å£ģ
    0.12
    å¢Ļ
    0.12
    å¢ĻéĿ¢
    0.11
    -wall
    0.11
    annes
    0.10
    æĮĤçĿĢ
    0.10
    åħ¬ç¤º
    0.10
     wall
    0.10
    è¾¾æłĩ
    0.10
    Activations Density 0.061%

    No Known Activations