© 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. 32045
    Prev
    Next
    INDEX
    Explanations

    peace and conflict

    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
    èĪįå¾Ĺ
    -0.11
    强åĬ¿
    -0.09
    æ²¥
    -0.09
    ará
    -0.09
    destruct
    -0.09
    æ¿Ģæĥħ
    -0.09
    æĪ³
    -0.09
     Tul
    -0.08
     raw
    -0.08
    rix
    -0.08
    POSITIVE LOGITS
    温æŁĶ
    0.14
    åĴĮå¹³
    0.13
    æŁĶåĴĮ
    0.12
    æŁĶ软
    0.12
    peace
    0.12
    温æĥħ
    0.12
    å¹³éĿĻ
    0.12
    温åĴĮ
    0.11
     peaceful
    0.11
     civilians
    0.11
    Activations Density 0.185%

    No Known Activations