© 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. 7826
    Prev
    Next
    INDEX
    Explanations

    S or s

    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
    ople
    -0.11
    uve
    -0.09
    ordo
    -0.09
    кÑĥÑĢ
    -0.09
    åĤį
    -0.09
    aths
    -0.08
     долж
    -0.08
    ogra
    -0.08
    å´©
    -0.08
    empo
    -0.08
    POSITIVE LOGITS
    ãģ¹ãģį
    0.10
    æİĸ
    0.09
    大ä¸ĵ
    0.09
    èľļ
    0.09
    æ¢
    0.09
    æĢ§è´¨
    0.09
    èĥ½åĬĽå¼º
    0.08
    RY
    0.08
    æ°ª
    0.08
    éķŃ
    0.08
    Activations Density 0.405%

    No Known Activations