© 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. 26643
    Prev
    Next
    INDEX
    Explanations

    at events or gatherings

    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
    éªĽ
    -0.11
    çĿ¡åīį
    -0.10
    iram
    -0.10
    涮
    -0.09
    å¢ī
    -0.09
    ues
    -0.09
    驺
    -0.09
    erner
    -0.09
    诤
    -0.09
    头çĸ¼
    -0.09
    POSITIVE LOGITS
    çİ°åľº
    0.12
    缼ä¼ļ
    0.12
     меÑĢопÑĢи
    0.12
    éŁ³ä¹IJä¼ļ
    0.11
     Teh
    0.10
     меÑĢопÑĢиÑıÑĤиÑı
    0.10
    à¸ĩาà¸Ļ
    0.10
     event
    0.09
    åĩºå¸Ń
    0.09
     attended
    0.09
    Activations Density 0.204%

    No Known Activations