© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22166
    Prev
    Next
    INDEX
    Explanations

    purchase price

    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
    åºĦ
    -0.10
    æĺİæĺİ
    -0.09
    èĦļä¸ĭ
    -0.09
    uide
    -0.09
    èİĬ
    -0.09
    宫殿
    -0.08
     велик
    -0.08
    .rdf
    -0.08
    ÙĪار
    -0.08
    ä¸Ģ缴
    -0.08
    POSITIVE LOGITS
    åħ¨æĹ¥
    0.10
    并ä¸įä¼ļ
    0.09
    注åĨĮèµĦæľ¬
    0.09
    æŃ¤ä¸¾
    0.09
    对åħ¶
    0.09
    çĽĬ
    0.08
    æĭĽåij¼
    0.08
    è¿Ļ家
    0.08
     ÙĨÙĤ
    0.08
    ãĤıãģļ
    0.08
    Activations Density 0.034%

    No Known Activations