© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40077
    Prev
    Next
    INDEX
    Explanations

    POWs and concentration camps

    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
    éĩıåĮĸ
    -0.09
    åĭĩ
    -0.09
     должноÑģÑĤ
    -0.09
    azers
    -0.09
    ä¸Ģåıª
    -0.08
    ãĤ¼
    -0.08
    究
    -0.08
    _REPEAT
    -0.08
    URES
    -0.08
    èģĺçĶ¨
    -0.08
    POSITIVE LOGITS
    æĬĺ磨
    0.12
    çĭ±
    0.10
    åĽļ
    0.10
    ä¿Ŀ管
    0.10
    åѤ
    0.10
    åĽ¹
    0.10
     Prison
    0.09
     prison
    0.09
    ä¿ĺ
    0.09
     cach
    0.09
    Activations Density 0.064%

    No Known Activations