© 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. 27904
    Prev
    Next
    INDEX
    Explanations

    civilian personnel or dual use

    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
    è¡¥
    -0.10
    ju
    -0.09
    ICON
    -0.09
    æĭľå¸Ī
    -0.08
     ju
    -0.08
    çĺģ
    -0.08
    æĤ´
    -0.08
    被åĬ¨
    -0.08
    æĶ¥
    -0.08
    /AP
    -0.08
    POSITIVE LOGITS
     civilian
    0.21
    æ°ijçĶ¨
    0.20
     civilians
    0.17
    å¹³æ°ij
    0.15
    æĹ¥å¸¸
    0.13
    æ°ij
    0.12
    æ°ijéĹ´
    0.12
    平常
    0.12
    çĻ¾å§ĵ
    0.12
     Civ
    0.11
    Activations Density 0.152%

    No Known Activations