© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8281
    Prev
    Next
    INDEX
    Explanations

    at/on/around locations

    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
     tape
    -0.10
     Tape
    -0.09
    swer
    -0.09
    麾
    -0.09
    çļĦ帮åĬ©
    -0.09
    æľĢ好æĺ¯
    -0.09
    æĺİæĹ¥
    -0.09
    gram
    -0.08
    æĺİæĺŁ
    -0.08
    身影
    -0.08
    POSITIVE LOGITS
    æ£
    0.10
    çļĦ人çī©
    0.09
    å³Ĵ
    0.09
    æłĭ
    0.09
    uffers
    0.09
     undert
    0.09
    å£ħ
    0.09
    åĽŀå¿Ĩ
    0.09
    管çIJĨåĴĮ
    0.08
     Undert
    0.08
    Activations Density 0.067%

    No Known Activations