© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14486
    Prev
    Next
    INDEX
    Explanations

    espionage terms, stealth, spyware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    å¾Ĺ罪
    -0.20
    èĪľ
    -0.20
    ç¾İçļĦ
    -0.20
    acks
    -0.20
    æĬķä¿Ŀ
    -0.19
    罡
    -0.18
    好çļĦ
    -0.18
    åĨ²
    -0.18
    èįīæ¡Ī
    -0.18
    åĪĩ
    -0.18
    POSITIVE LOGITS
    éļIJèĶ½
    0.28
    olina
    0.20
     stealth
    0.19
    æįķ
    0.18
     WIN
    0.18
    æĹłå£°
    0.18
    éĴ¿
    0.18
    tif
    0.18
     silently
    0.18
    éļIJèĹı
    0.18
    Activations Density 0.015%

    No Known Activations