© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12238
    Prev
    Next
    INDEX
    Explanations

    burial sites and tombs

    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
    è¿ĩæĿ¥
    -0.21
     otherwise
    -0.19
    anc
    -0.19
    大å¹ħ度
    -0.18
    ç´§å¯Ĩ
    -0.18
    ä¸Ńç§ĭ
    -0.18
    å¹³æŶ
    -0.18
     H
    -0.18
     resembl
    -0.18
     Sah
    -0.18
    POSITIVE LOGITS
    çķĻä¸ĭäºĨ
    0.22
    帰
    0.21
    åľ¨å½ĵåľ°
    0.19
    cow
    0.19
    ä¸īå±Ĥ
    0.19
    æĪIJ为ä¸ĢåIJį
    0.19
    çķ¶åľ°
    0.19
    äºĨä»ĸçļĦ
    0.18
     oci
    0.18
    cÃŃ
    0.18
    Activations Density 0.013%

    No Known Activations