© 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. 22434
    Prev
    Next
    INDEX
    Explanations

    to learn or try something new

    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
    ç¥ĿæĦ¿
    -0.10
    ç²¼
    -0.09
    鸡汤
    -0.09
    æ®ĥ
    -0.09
    禺
    -0.09
    çľ¼çļ®
    -0.09
    è¿ĻçĤ¹
    -0.09
    åīįè¡Į
    -0.09
    ihan
    -0.08
    èģªæĺİ
    -0.08
    POSITIVE LOGITS
    æŃ£å½ĵ
    0.09
    igate
    0.08
    深度
    0.08
    влек
    0.08
    ira
    0.08
    åıĺæĪIJ
    0.08
     Chains
    0.08
     Arena
    0.08
    æŃ£å¼ı
    0.08
    HM
    0.08
    Activations Density 0.184%

    No Known Activations