© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53038
    Prev
    Next
    INDEX
    Explanations

    would have

    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
    å´©
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.09
    å¼Ħ
    -0.09
     görün
    -0.09
     Dort
    -0.09
    å¾ĪæŃ£å¸¸
    -0.09
     unravel
    -0.08
    è¿ħ
    -0.08
    aney
    -0.08
    çĶŁæľº
    -0.08
    POSITIVE LOGITS
    æľīè¿ĩ
    0.10
    个交æĺĵ
    0.09
     Lottery
    0.09
    вал
    0.09
    æı´
    0.09
     has
    0.08
    ä¸Ńæĸ¹
    0.08
     AVC
    0.08
    ppers
    0.08
     telah
    0.08
    Activations Density 0.100%

    No Known Activations