© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 33252
    Prev
    Next
    INDEX
    Explanations

    was the first

    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
    çĥŁåĽ±
    -0.09
    åŃIJåŃĻ
    -0.09
    æ°¸æģĴ
    -0.09
    æĸ°èµĽåŃ£
    -0.09
     currently
    -0.09
    TL
    -0.09
    çĽ¸ä¿¡å¤§å®¶
    -0.09
    å§»
    -0.08
    æŃ¤åĪ»
    -0.08
    ä»Ĭ天æĪij们
    -0.08
    POSITIVE LOGITS
    å¾Īéķ¿æĹ¶éĹ´
    0.13
    å¾Īåĸľæ¬¢
    0.10
    ä¸įæĸŃçļĦ
    0.10
     originally
    0.10
     ÑĢанÑĮÑĪе
    0.10
    æĹłæķ°æ¬¡
    0.09
    æĸĽ
    0.09
    æĪij以为
    0.09
    æĬµ
    0.09
     вÑģегда
    0.09
    Activations Density 0.190%

    No Known Activations