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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52070
    Prev
    Next
    INDEX
    Explanations

    string formatting

    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
    omat
    -0.10
    è¾IJ
    -0.08
     crem
    -0.08
    UTO
    -0.08
    å®¡æŁ¥
    -0.08
    åħ¨å¤©
    -0.08
    à¸Ľà¸£à¸°
    -0.07
    åIJĦèĩª
    -0.07
    å°¼äºļ
    -0.07
     Mighty
    -0.07
    POSITIVE LOGITS
    ä¸įçķĻ
    0.10
    å¤ĦçIJĨåĻ¨
    0.09
    åĶ³
    0.09
    å¿ĥè¡Ģ
    0.09
    roker
    0.09
    thin
    0.09
    anut
    0.09
    æł·çļĦ
    0.09
    æĪij们éĥ½
    0.09
     hous
    0.08
    Activations Density 0.250%

    No Known Activations