© 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. 33650
    Prev
    Next
    INDEX
    Explanations

    peace and war contexts

    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
    æķ¢
    -0.10
    åħ¥å¸Ĥ
    -0.09
    éĹ¯
    -0.09
    å·¥åķĨå±Ģ
    -0.09
    ä¸Ģ头
    -0.08
    æĻļ
    -0.08
    combe
    -0.08
    é£İæĥħ
    -0.08
    æĶ¯éĺŁ
    -0.08
     Atkins
    -0.08
    POSITIVE LOGITS
    åĴĮå¹³
    0.21
    æĪĺäºī
    0.19
     peace
    0.18
    peace
    0.17
     Peace
    0.17
    Peace
    0.16
    æīĵä»Ĺ
    0.14
     войнÑĭ
    0.13
    åĨ²çªģ
    0.13
     war
    0.13
    Activations Density 0.126%

    No Known Activations