© 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. 12449
    Prev
    Next
    INDEX
    Explanations

    last time

    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
    åĪĿå§ĭ
    -0.23
    ä»ĬåIJİ
    -0.21
    åĪ°æŶåĢĻ
    -0.21
    OTES
    -0.21
    éļıåIJİ
    -0.20
    åIJİæľŁ
    -0.20
    åIJİç»Ń
    -0.20
    åīįæľŁ
    -0.20
    é¦ĸ次
    -0.20
     initially
    -0.20
    POSITIVE LOGITS
    /current
    0.27
    ä¸Ĭ次
    0.26
    è§ģéĿ¢
    0.21
     اÙĦÙħاض
    0.20
    为æŃ¢
    0.20
    OrDefault
    0.19
    Mix
    0.19
    æĭĽèĤ¡ä¹¦
    0.19
    æī¿
    0.19
    æ¯ĶèµĽ
    0.19
    Activations Density 0.053%

    No Known Activations