© 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. 21036
    Prev
    Next
    INDEX
    Explanations

    comments or post status

    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
    éŃĤ
    -0.09
    ls
    -0.09
    ols
    -0.08
    é¢ł
    -0.08
    å·ħ
    -0.08
    ä¸įç»ı
    -0.08
    remember
    -0.08
    cccc
    -0.08
    ument
    -0.08
     пÑĢид
    -0.08
    POSITIVE LOGITS
    azor
    0.09
    strup
    0.09
    交æµģ
    0.09
    深深çļĦ
    0.09
    å¯Ĥå¯ŀ
    0.09
     ISP
    0.09
    æļ§
    0.09
    çİ·
    0.08
    .jupiter
    0.08
    æīĵæī«
    0.08
    Activations Density 0.144%

    No Known Activations