© 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. 11883
    Prev
    Next
    INDEX
    Explanations

    security codes and passwords

    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
    å°Ŀ
    -0.10
    æĪ´çĿĢ
    -0.10
    èį¡
    -0.09
    çķ¸
    -0.09
     backs
    -0.08
    æĶ¹éĿ©
    -0.08
     bó
    -0.08
     Cra
    -0.08
    åĩłä¸ªäºº
    -0.08
    èŀĥèŁ¹
    -0.08
    POSITIVE LOGITS
    ä¸ĵ人
    0.10
    Ñģоб
    0.09
    åĮĻ
    0.09
    lish
    0.09
     ни
    0.09
    æĢ¥åī§
    0.08
    à¸IJาà¸Ļ
    0.08
    ÑĢоÑĪ
    0.08
    AME
    0.08
    妥åĸĦ
    0.08
    Activations Density 0.016%

    No Known Activations