© 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. 37556
    Prev
    Next
    INDEX
    Explanations

    grocery stores and shopping

    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
    åѤåįķ
    -0.10
    人æ°ijæľįåĬ¡
    -0.09
    çĹ¹
    -0.09
    çľģåĨħ
    -0.09
     Petty
    -0.09
    é¹ħ
    -0.08
    æĪijçľģ
    -0.08
    å¤Ļ
    -0.08
     Kelley
    -0.08
    æŶéĹ´åĨħ
    -0.08
    POSITIVE LOGITS
    èģĨåIJ¬
    0.10
    åħ¨ä½ĵåijĺå·¥
    0.09
    è¿Ľå±ķæĥħåĨµ
    0.09
    è¢ĭ
    0.09
    FromString
    0.08
    ylim
    0.08
    FLT
    0.08
    票
    0.08
    åĮ¹
    0.08
    å¿ħè¦ģçļĦ
    0.08
    Activations Density 0.009%

    No Known Activations