© 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. 13616
    Prev
    Next
    INDEX
    Explanations

    occult, witchcraft, secret societies

    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
    åIJĦåįķä½į
    -0.21
    èī¯æĢ§
    -0.20
    ä½ľèĢħæľ¬äºº
    -0.19
    nof
    -0.19
    ä¸įåħ¬å¹³
    -0.19
    çĸ¼
    -0.19
    æĪĺçģ«
    -0.18
    åIJĦéĥ¨éŨ
    -0.18
    å¾ĩ
    -0.18
    ingly
    -0.17
    POSITIVE LOGITS
    仪å¼ı
    0.21
    èĵĦ
    0.21
     rituals
    0.19
    -themed
    0.19
     Bauer
    0.18
    éĺ´
    0.18
    å¥ij约
    0.18
    èģļä¼ļ
    0.18
    coni
    0.17
    å´ĩæĭľ
    0.17
    Activations Density 0.010%

    No Known Activations