© 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. 12971
    Prev
    Next
    INDEX
    Explanations

    adverse effects and toxicity

    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
    erten
    -0.22
    çĭŃ
    -0.21
    æĸ¹åľĨ
    -0.21
    odyn
    -0.20
    è¿Ļ个åIJįåŃĹ
    -0.20
    æĦıåij³çĿĢ
    -0.20
    sst
    -0.20
    åĴĮå¹³
    -0.20
    åĮħåĽ´
    -0.20
    æĮijéĢī
    -0.19
    POSITIVE LOGITS
    ãĥªãĤ¹ãĤ¯
    0.28
    åī¯ä½ľçĶ¨
    0.27
    é£İéĻ©
    0.26
    éļIJæĤ£
    0.25
    諸
    0.24
    çļĦé£İéĻ©
    0.24
     risk
    0.23
     ë°ľìĥĿ
    0.23
     safety
    0.22
    風éļª
    0.22
    Activations Density 0.186%

    No Known Activations