© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52954
    Prev
    Next
    INDEX
    Explanations

    civilians and innocent people

    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
    ç§ĺ
    -0.10
    å¥ĭè¿Ľ
    -0.09
    媳å¦ĩ
    -0.09
     Draft
    -0.09
    /unit
    -0.09
    é¢Ĩä¼ļ
    -0.09
     phấn
    -0.08
    [unit
    -0.08
    ACL
    -0.08
     ÑĥпÑĢав
    -0.08
    POSITIVE LOGITS
    æĹłè¾ľ
    0.24
     innocent
    0.17
     civilian
    0.14
     innoc
    0.13
     civilians
    0.13
    å¹³æ°ij
    0.13
     innocence
    0.12
     Innoc
    0.12
    è¾ľ
    0.11
    æ°ijçĶ¨
    0.11
    Activations Density 0.195%

    No Known Activations