© 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. 16266
    Prev
    Next
    INDEX
    Explanations

    taking or losing possessions

    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
    æ¯ıéĢ¢
    -0.20
    åĵģç±»
    -0.19
    ification
    -0.19
     Conc
    -0.19
     usher
    -0.18
     adm
    -0.18
    æݨ广
    -0.18
    kir
    -0.18
    posed
    -0.17
    å¢Ļå£ģ
    -0.17
    POSITIVE LOGITS
    ç¢İçīĩ
    0.25
    丢失
    0.22
    交ç»Ļ
    0.21
     ÑģÑĤоим
    0.21
    åįĸç»Ļ
    0.20
    èµĽåIJİ
    0.19
    ilos
    0.19
     USED
    0.19
    被çĽĹ
    0.19
     exchange
    0.19
    Activations Density 0.129%

    No Known Activations