© 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. 11137
    Prev
    Next
    INDEX
    Explanations

    restore, recover, lost items

    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
    çľĭçĤ¹
    -0.21
    åijĬè¯īä½ł
    -0.19
     Leon
    -0.19
    åħ±åĴĮåĽ½
    -0.19
    ä¼ĺ
    -0.19
     contraction
    -0.18
    ÙĬÙĬÙĨ
    -0.18
    èĩªåĪ¶
    -0.18
     ÙĪاÙĦØŃ
    -0.17
    trad
    -0.17
    POSITIVE LOGITS
    æī¾åĽŀ
    0.36
    æģ¢å¤į
    0.34
    丢失
    0.32
    è¿ĺåİŁ
    0.28
     restore
    0.27
    ä¿Ŀ管
    0.27
     restoration
    0.26
    Lost
    0.26
     Restoration
    0.25
    Recovered
    0.25
    Activations Density 0.076%

    No Known Activations