© 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. 17135
    Prev
    Next
    INDEX
    Explanations

    exploit, advantage, opportunity, looting, benefit, available

    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
    éĢĶä¸Ń
    -0.10
    éĻ¢
    -0.09
     lab
    -0.09
    说åĪ°è¿ĻéĩĮ
    -0.09
    å¯Įè´µ
    -0.09
    éĻ¢åī¯éĻ¢éķ¿
    -0.09
    éĻ¢éĻ¢éķ¿
    -0.09
    åĽº
    -0.08
     Wolff
    -0.08
    ç¹ģçIJIJ
    -0.08
    POSITIVE LOGITS
    è¶ģ
    0.23
    æľºä¼ļ
    0.15
     opport
    0.14
    è¶ģçĿĢ
    0.13
     aprove
    0.13
     opportun
    0.13
    赶紧
    0.12
    æľºéģĩ
    0.12
    ä»İä¸Ń
    0.12
    çļĦæľºä¼ļ
    0.12
    Activations Density 0.085%

    No Known Activations