© 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. 62741
    Prev
    Next
    INDEX
    Explanations

    sacrifice and trade-offs

    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
    ä¼ļç»Ļ
    -0.10
     вал
    -0.10
    幸
    -0.10
    两次
    -0.10
    追赶
    -0.10
    åIJ¯è¿ª
    -0.09
    èµĦè´¨
    -0.09
    lane
    -0.09
    åĮĿ
    -0.09
    Unsafe
    -0.09
    POSITIVE LOGITS
    çīºçī²
    0.28
     sacrifice
    0.22
     sacrifices
    0.20
     Sacr
    0.19
     sacrificing
    0.19
     sacrificed
    0.18
    çĬ
    0.18
     sacrific
    0.17
    æĶ¾å¼ĥ
    0.16
    acr
    0.16
    Activations Density 0.082%

    No Known Activations