© 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. 49148
    Prev
    Next
    INDEX
    Explanations

    fashion trends

    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
    å½»
    -0.09
    รà¸Ń
    -0.08
    å¸Ń
    -0.08
    ECT
    -0.08
    æ±ĤèģĮ
    -0.08
    èĤĮ
    -0.08
    åĴª
    -0.08
    å¾Ĺ天çĭ¬åİļ
    -0.08
     Raq
    -0.08
    å¢Ļä¸Ĭ
    -0.08
    POSITIVE LOGITS
    æ½®æµģ
    0.19
    æµģè¡Į
    0.17
     trends
    0.16
    æµģè¡ĮçļĦ
    0.16
    è¶ĭåĬ¿
    0.15
     trend
    0.15
     Trends
    0.14
    æŶ髦
    0.12
    æŶå°ļ
    0.12
    çļĦè¶ĭåĬ¿
    0.12
    Activations Density 0.035%

    No Known Activations