© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31228
    Prev
    Next
    INDEX
    Explanations

    activities, sightseeing, hotel, do

    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
    çĦī
    -0.11
    é«ĺ级
    -0.10
    è¯ĺ
    -0.09
    åł°
    -0.09
    _UL
    -0.09
    ihar
    -0.09
    ableView
    -0.09
    çĶĺ
    -0.08
    åĪ®
    -0.08
    rase
    -0.08
    POSITIVE LOGITS
    åģĩæĹ¥
    0.09
    æĸ°ä¸ļæĢģ
    0.09
    æĸĩ娱
    0.09
    ç»ij
    0.09
    terra
    0.09
    _OPTIONS
    0.08
    娱
    0.08
    ä¹°äºĨ
    0.08
    åĪĴ
    0.08
    代åĬŀ
    0.08
    Activations Density 0.102%

    No Known Activations