© 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. 10075
    Prev
    Next
    INDEX
    Explanations

    arms, weapons, or armament systems

    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
    æij¸
    -0.10
    ä¸įèĪį
    -0.09
    æį¨
    -0.09
     Lik
    -0.09
     squeez
    -0.08
    åĩĢèµĦ产
    -0.08
    å½ĵä¹ĭ
    -0.08
    æŀ¹
    -0.08
    ç»ıèIJ¥èĢħ
    -0.08
    æĻ¤
    -0.08
    POSITIVE LOGITS
    çī¹èī²å°ıéķĩ
    0.10
    è£ħå¤ĩ
    0.09
    æĪ¿
    0.09
    åºĵ
    0.09
    etus
    0.08
    nings
    0.08
    çī¹éķ¿
    0.08
    æĮĤåľ¨
    0.08
    çī¹èī²
    0.08
    kö
    0.08
    Activations Density 0.027%

    No Known Activations