© 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. 15685
    Prev
    Next
    INDEX
    Explanations

    near death and soul experiences

    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
    ãģĬäºĴ
    -0.23
    æĺ¨
    -0.22
    è¹²
    -0.21
    管çIJĨæ°´å¹³
    -0.21
    anken
    -0.20
    olib
    -0.20
    æĺ¨æĹ¥
    -0.20
    éĩİçĶŁ
    -0.20
    åħ¬çĶ¨
    -0.20
    è¦ĨçĽĸçİĩ
    -0.20
    POSITIVE LOGITS
    æī§
    0.22
    ame
    0.21
     "
    0.21
    çĤ
    0.21
     coma
    0.21
    ç»ıåİĨ
    0.20
    "
    0.20
    çĸ¤çĹķ
    0.20
     normal
    0.20
    ä½ĵéªĮ
    0.20
    Activations Density 0.016%

    No Known Activations