© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37727
    Prev
    Next
    INDEX
    Explanations

    daily life and activity

    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
    åѤ
    -0.10
    åħ¥ãĤĬ
    -0.10
     اÙĦÙĦج
    -0.10
    æŃ¥æŃ¥
    -0.10
    æĪIJé¾Ļ
    -0.10
    以èī²
    -0.09
    èĦ±ç¦»
    -0.09
    è¶Ĭ
    -0.09
    æĭĽåĭŁ
    -0.09
    bird
    -0.09
    POSITIVE LOGITS
    æĹ¥å¸¸çĶŁæ´»
    0.14
    æĹ¥å¸¸å·¥ä½ľ
    0.12
    å¹³åĩ¡
    0.11
    çĶŁæ´»çļĦ
    0.11
    çĶŁæ´»
    0.10
    æĹ¥å¸¸
    0.10
    åĮĨåĮĨ
    0.09
     usual
    0.09
    çĶŁæ´»ä¸Ń
    0.09
     daily
    0.09
    Activations Density 0.068%

    No Known Activations