© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 12144
    Prev
    Next
    INDEX
    Explanations

    reduction in weight

    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
    å®īæĬļ
    -0.19
    æŃ£ç¡®çļĦ
    -0.18
    oce
    -0.18
    对ä¼ģä¸ļ
    -0.18
    åıijå±ķ壮大
    -0.18
    Ã¤ÃŁ
    -0.18
    urate
    -0.18
    åıĹçģ¾
    -0.18
    åľºéĿ¢
    -0.18
     br
    -0.18
    POSITIVE LOGITS
    å¢ŀåĬł
    0.22
    é¢Ŀå¤ĸ
    0.22
    ä¸įå¿ħè¦ģçļĦ
    0.21
    太å¤ļçļĦ
    0.20
    leÅŁ
    0.20
    deen
    0.20
    人åĬĽ
    0.20
    ä¸ķ
    0.19
    æī®
    0.19
    å¢ŀåĬłäºĨ
    0.19
    Activations Density 0.109%

    No Known Activations