© 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. 38575
    Prev
    Next
    INDEX
    Explanations

    just [qualifier]

    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
    олÑĮзов
    -0.10
    æł¹æľ¬å°±ä¸į
    -0.10
    igin
    -0.09
    å¶Ĥ
    -0.09
    æł¹æľ¬
    -0.09
    ãĥ¡ãĥª
    -0.09
    æĪĬ
    -0.09
    ç°Į
    -0.09
    åĪ«è¯´
    -0.08
    纡
    -0.08
    POSITIVE LOGITS
    å®Įå·¥
    0.10
    æľīæīĢ
    0.09
    ä¸ĢçĤ¹åĦ¿
    0.08
    饺
    0.08
    æĬĢ
    0.08
    åī
    0.08
    çļĦ带é¢Ĩ
    0.08
    çĤ¹åĦ¿
    0.08
    åħ¬è®¤çļĦ
    0.08
    ament
    0.08
    Activations Density 0.028%

    No Known Activations