© 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. 23729
    Prev
    Next
    INDEX
    Explanations

    purchasing power and consumer decisions

    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
    èľ¿
    -0.09
    çĻ¾å®¶
    -0.09
    æĪĺéĺŁ
    -0.09
    issance
    -0.09
    亲çĪ±
    -0.09
    é£ĺ
    -0.08
    altimore
    -0.08
    çĽĺ
    -0.08
    CTSTR
    -0.08
    å¼łæī¬
    -0.08
    POSITIVE LOGITS
    æ¶Īè´¹
    0.21
    æ¶Īè´¹éľĢæ±Ĥ
    0.19
    è´Ńä¹°
    0.19
    æ¶Īè´¹èĢħ
    0.18
    æ¶Īè´¹èĢħçļĦ
    0.17
     consumer
    0.17
    æ¶Īè²»
    0.17
     purchasing
    0.17
     buying
    0.14
     consumers
    0.14
    Activations Density 0.083%

    No Known Activations