© 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. 8466
    Prev
    Next
    INDEX
    Explanations

    access, employee, accounts, management, databases

    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
    æŀ¢
    -0.11
    âį¨
    -0.09
    æ¡Ĩ
    -0.09
    è¾¹éĻħ
    -0.09
     Fortune
    -0.09
    åĽŀå¿Ĩ
    -0.09
    æĺ¯ä¸Ģ座
    -0.09
    èĦ²
    -0.09
    åīįæıIJæĺ¯
    -0.09
    _gpu
    -0.09
    POSITIVE LOGITS
    èģĮä½į
    0.10
    ä»»èģĮ
    0.10
    (pad
    0.09
    å²Ĺä½į
    0.09
    èģĮåĬ¡
    0.09
    访éĹ®
    0.09
     Serge
    0.08
    oque
    0.08
    å¹²éĥ¨
    0.08
    åIJ¸
    0.08
    Activations Density 0.055%

    No Known Activations