© 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. 56961
    Prev
    Next
    INDEX
    Explanations

    grocery and retail 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
     waitress
    -0.09
    èį
    -0.09
    ä¼ĹçĶŁ
    -0.09
    æľįåĬ¡åijĺ
    -0.09
     dine
    -0.09
     waiter
    -0.08
    (wait
    -0.08
    rowse
    -0.08
    åķĨä¸ļéĵ¶è¡Į
    -0.08
    atis
    -0.08
    POSITIVE LOGITS
    åı¨
    0.10
    秫
    0.09
    èĪĨæĥħ
    0.09
    unte
    0.09
    åIJĦéĥ¨éŨ
    0.09
    éŃĤ
    0.09
    oha
    0.09
    æĿ¥çĶµ
    0.09
    ä¸ĭçıŃ
    0.08
    æķıæį·
    0.08
    Activations Density 0.022%

    No Known Activations