© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48434
    Prev
    Next
    INDEX
    Explanations

    retail stores and brands

    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
    æĪ´çĿĢ
    -0.09
    èĩªçIJĨ
    -0.09
     exc
    -0.08
    achu
    -0.08
    åĮı
    -0.08
     excuse
    -0.08
    å¼ĢåıijåĪ©çĶ¨
    -0.08
    alach
    -0.08
     Kot
    -0.08
    大åºĨ
    -0.08
    POSITIVE LOGITS
    ä»ĭ
    0.10
    евиÑĩ
    0.10
    rze
    0.10
    å¹ķ
    0.10
    ivor
    0.09
    ariat
    0.09
    æ¯ıä¸Ģ次
    0.09
    -io
    0.09
     Wing
    0.09
     alternative
    0.08
    Activations Density 0.006%

    No Known Activations