© 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. 20943
    Prev
    Next
    INDEX
    Explanations

    Texas place names

    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
     fro
    -0.09
    åľ¨åĮĹ京
    -0.09
    åł¤
    -0.09
    è®¤çľŁåŃ¦ä¹ł
    -0.08
    é¾Ļæ¹ĸ
    -0.08
     hors
    -0.08
    西æ¹ĸ
    -0.08
    IFF
    -0.08
    触
    -0.08
    æ¯ı天éĥ½
    -0.08
    POSITIVE LOGITS
    èĿ®
    0.10
    çħ¤
    0.09
    STEM
    0.09
    ÑĤÑıж
    0.09
    ç¬ı
    0.08
    æ³ķ人
    0.08
    ï¹Ģ
    0.08
    åªĴ
    0.08
     TableCell
    0.08
    .blogspot
    0.08
    Activations Density 0.206%

    No Known Activations