© 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. 11861
    Prev
    Next
    INDEX
    Explanations

    military personnel, veterans, workers

    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
    éĢıè¿ĩ
    -0.10
    epad
    -0.10
    ivy
    -0.09
    æŁĶåĴĮ
    -0.09
    ç¨Ģ缺
    -0.09
    sav
    -0.09
    æ¬
    -0.09
    omat
    -0.08
    åĮ»å¸Ī
    -0.08
    产æĿĥ
    -0.08
    POSITIVE LOGITS
    æļ´éľ²
    0.08
    人群
    0.08
     densely
    0.08
    .Logic
    0.08
    åħ¬ä¼Ĺ
    0.08
    èģĤ
    0.08
    åħ¬åħ±åľºæīĢ
    0.07
    å¹³åĿĩæ¯ı
    0.07
    çī¹åĪ«æĺ¯
    0.07
    æĸ°å»º
    0.07
    Activations Density 0.389%

    No Known Activations