© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20721
    Prev
    Next
    INDEX
    Explanations

    South Africa, Swaziland

    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¸įå®Į
    -0.10
    æĤ¬æµ®
    -0.09
    ä¼ļè®©ä½ł
    -0.09
    éĤķ
    -0.09
    åĨľå®¶ä¹IJ
    -0.09
    éĴĪ对æĢ§
    -0.09
    缴è¾ĸ
    -0.09
    PageIndex
    -0.09
    æ¿ł
    -0.08
    ç¼ľ
    -0.08
    POSITIVE LOGITS
    竽
    0.09
    ItemAt
    0.09
    æĺİå¹´
    0.09
    илÑĮно
    0.08
    gü
    0.08
    atos
    0.08
    èĩªçĶ±
    0.08
     Jar
    0.08
    çİĭåĽ½
    0.08
    8
    0.08
    Activations Density 0.157%

    No Known Activations