© 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. 15519
    Prev
    Next
    INDEX
    Explanations

    Holocaust and related atrocities

    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
    æľīåĪ©
    -0.23
     nghè
    -0.23
    稳
    -0.22
    座è°Ī
    -0.22
    åĸľ
    -0.22
    ç¥ŀä»Ļ
    -0.21
     Monad
    -0.21
    éĤ¸
    -0.20
    åı£å¾Ħ
    -0.20
    ãĥijãĥijæ´»
    -0.20
    POSITIVE LOGITS
     atrocities
    0.30
     Holocaust
    0.30
    æĤ²åī§
    0.25
    ç½Ħ
    0.24
     Auschwitz
    0.24
    éģĹ
    0.24
    æĤ²
    0.23
    人æĿĥ
    0.23
     horrors
    0.23
    åİĨåı²
    0.23
    Activations Density 0.078%

    No Known Activations