© 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. 8577
    Prev
    Next
    INDEX
    Explanations

    long durations

    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
    马æĭī
    -0.10
    à¸ģระà¸Ī
    -0.10
    éĢĤæŶ
    -0.09
    éķ¿çĽ¸
    -0.09
    æŶåĪ»
    -0.09
    åIJİéĿ¢çļĦ
    -0.09
    äºĽ
    -0.09
    ron
    -0.08
    æĬ¢
    -0.08
     pref
    -0.08
    POSITIVE LOGITS
     ÙĦÙħدة
    0.14
     lasted
    0.14
    åİĨæŶ
    0.12
     duration
    0.12
    ä¹ħäºĨ
    0.12
    æķ´æķ´
    0.11
    éķ¿è¾¾
    0.11
    .duration
    0.11
    Duration
    0.11
     Duration
    0.11
    Activations Density 0.198%

    No Known Activations