© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12205
    Prev
    Next
    INDEX
    Explanations

    consumer purchasing and demand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    微信åħ¬ä¼Ĺ
    -0.21
    æķĻ导
    -0.20
    ä»ħä¾Ľ
    -0.19
    人åĵ¡
    -0.19
    GTK
    -0.19
    ä½łèĩªå·±
    -0.19
    æ·±åħ¥å¼Ģå±ķ
    -0.19
    ä¸įæŃ»
    -0.18
    åīįæĸ¹
    -0.18
    对æĪijæĿ¥è¯´
    -0.18
    POSITIVE LOGITS
    æ¶Īè´¹
    0.31
    è´Ńä¹°
    0.30
    æ¶Īè´¹åįĩ级
    0.29
    åĩºè¡Į
    0.28
    æ¶Īè´¹éľĢæ±Ĥ
    0.28
     preferences
    0.27
     purchasing
    0.26
     buying
    0.25
    /preferences
    0.25
    preferences
    0.24
    Activations Density 0.103%

    No Known Activations