© 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. 53322
    Prev
    Next
    INDEX
    Explanations

    RFID and smart tags

    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
    ä¸ļä½Ļ
    -0.10
    å¦į
    -0.09
    ä¹Ķ丹
    -0.09
    æ§İ
    -0.09
    æ®Ĭ
    -0.09
     Axe
    -0.08
    æĸ©
    -0.08
    æĸ
    -0.08
    å¼ŁåħĦ
    -0.08
    æĸ«
    -0.08
    POSITIVE LOGITS
    æĦŁåºĶ
    0.10
    åĮĹæĸĹ
    0.10
    空æ°Ķä¸Ń
    0.09
    享çĶ¨
    0.09
    é»Ħæĺı
    0.09
    åħļåĴĮæĶ¿åºľ
    0.08
     Townsend
    0.08
     Scenario
    0.08
    ardu
    0.08
    enties
    0.08
    Activations Density 0.160%

    No Known Activations