© 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. 37639
    Prev
    Next
    INDEX
    Explanations

    news sources

    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
    wik
    -0.10
    çĽĺ
    -0.10
    æ¸Ĺ
    -0.09
    éĩįéĩį
    -0.09
    ëĭ¹
    -0.09
    /layouts
    -0.09
    è¹
    -0.08
    累累
    -0.08
    é¢ĨåĨĽ
    -0.08
    kek
    -0.08
    POSITIVE LOGITS
    ÑĮÑİ
    0.09
    åIJ»
    0.08
    straints
    0.08
    èĨı
    0.08
    ØŃظ
    0.08
    -upper
    0.08
    _android
    0.08
    /Card
    0.08
    读èĢħ
    0.08
    ä»İåīį
    0.08
    Activations Density 0.002%

    No Known Activations