© 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. 12225
    Prev
    Next
    INDEX
    Explanations

    starts of phrases

    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¿Į
    -0.20
    éŃħ
    -0.18
    åıĤçħ§
    -0.18
    âĪļ
    -0.18
    åĨ·éĿĻ
    -0.18
    âĪľ
    -0.18
    åĺīå¹´
    -0.17
     bác
    -0.17
    евÑĭÑħ
    -0.17
     abuses
    -0.17
    POSITIVE LOGITS
    åħ¨æĸ°çļĦ
    0.32
    æĸ°çļĦä¸Ģ
    0.30
    ä¸Ģ个æĸ°çļĦ
    0.29
    åħ¨æĸ°
    0.28
    è¿İæĿ¥äºĨ
    0.28
    æľ¬æ¬¡
    0.26
    æĸ°çļĦ
    0.26
    æĸ°ç¯ĩç«ł
    0.26
    è¿Ļä¸Ģ次
    0.24
    é¦ĸ个
    0.24
    Activations Density 0.229%

    No Known Activations