© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2945
    Prev
    Next
    INDEX
    Explanations

    regulatory and legal compliance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     concrete
    -0.26
    宽度
    -0.25
     dashed
    -0.25
    æĹłç¼ĺ
    -0.25
    ä¸ĬçıŃæĹı
    -0.24
     fan
    -0.24
     thr
    -0.23
     rear
    -0.23
    svp
    -0.23
     fans
    -0.23
    POSITIVE LOGITS
    æ³ķå¾ĭæ³ķè§Ħ
    0.47
    æ³ķè§Ħ
    0.47
     laws
    0.42
     governmental
    0.40
    æĶ¿åºľéĥ¨éŨ
    0.40
     regulations
    0.38
    æĶ¿åºľ
    0.35
     governing
    0.35
     government
    0.34
     regulatory
    0.34
    Activations Density 0.058%

    No Known Activations