© 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. 8707
    Prev
    Next
    INDEX
    Explanations

    exam preparation and study

    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
    æĭľå¸Ī
    -0.09
    ä¸ĭä¸Ģ个
    -0.09
    æĿł
    -0.09
    ett
    -0.09
    æݢ索
    -0.08
    ipient
    -0.08
    è§
    -0.08
    åıij表äºĨ
    -0.08
    æ³¼
    -0.08
    æŃª
    -0.08
    POSITIVE LOGITS
    å¤įä¹ł
    0.20
    å¤ĩèĢĥ
    0.19
    å¤ĩæĪĺ
    0.15
     preparation
    0.13
    åĩĨå¤ĩ
    0.13
    åĨ²åĪº
    0.12
     preparations
    0.12
     подгоÑĤов
    0.12
     Preparation
    0.12
    æºĸåĤĻ
    0.11
    Activations Density 0.040%

    No Known Activations