© 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. 12374
    Prev
    Next
    INDEX
    Explanations

    stages of life or age

    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
    ä¼ģåĽ¾
    -0.21
    ickt
    -0.20
    éľģ
    -0.20
    åĽ½æľīèµĦ产
    -0.20
    å¾Ĺ天
    -0.19
    ä¸įæ¸ħ
    -0.19
    æľªç»ı
    -0.19
    .TRAN
    -0.19
    å°§
    -0.19
    unce
    -0.18
    POSITIVE LOGITS
     gar
    0.25
    æī¶
    0.24
     Gar
    0.24
    Gar
    0.23
    å½ĵå¹´
    0.23
    绾
    0.21
    æŃ¥åħ¥
    0.20
    gar
    0.20
     모ìĬµ
    0.20
    å¥Ķèµ´
    0.18
    Activations Density 0.045%

    No Known Activations