© 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. 21193
    Prev
    Next
    INDEX
    Explanations

    future

    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
    说äºĨ
    -0.10
    æ¢ĵ
    -0.09
    born
    -0.08
    åģľçķĻ
    -0.08
     Born
    -0.08
    sted
    -0.08
    &P
    -0.08
    pu
    -0.08
     pans
    -0.08
    sss
    -0.08
    POSITIVE LOGITS
    æľªæĿ¥
    0.27
    æľªæĿ¥åıijå±ķ
    0.26
    æľªæĿ¥çļĦ
    0.26
     future
    0.24
    æľªä¾Ĩ
    0.23
    future
    0.21
    å°ĨæĿ¥
    0.21
     Future
    0.18
     futures
    0.18
     미ëŀĺ
    0.18
    Activations Density 0.044%

    No Known Activations