© 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. 49024
    Prev
    Next
    INDEX
    Explanations

    free riding

    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
    æĪİ
    -0.10
    容
    -0.10
    ç£Ķ
    -0.09
    壤
    -0.09
    å¥ī
    -0.09
    åij½
    -0.09
    念
    -0.09
     нем
    -0.09
    .sections
    -0.08
    ÑĩиÑĤ
    -0.08
    POSITIVE LOGITS
     McCabe
    0.10
    欺è¯Ī
    0.09
    ç»ıæµİåѦ
    0.09
    好æ¶Īæģ¯
    0.09
    çļĦä¿¡ä»»
    0.09
    ä¸Ģ楼
    0.08
    ç¥ŀä»Ļ
    0.08
    çĽijçĿ£
    0.08
    è³´
    0.08
    åĪĽ
    0.08
    Activations Density 0.020%

    No Known Activations