© 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. 13111
    Prev
    Next
    INDEX
    Explanations

    stock tickers

    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
    @student
    -0.21
     tal
    -0.20
     Atat
    -0.19
    ems
    -0.19
    æīį
    -0.19
    èı½
    -0.18
    åħ»æĪIJ
    -0.18
    满æĦı
    -0.18
    æķ¬
    -0.18
    uis
    -0.18
    POSITIVE LOGITS
    ä¹ĭ称
    0.21
    èĬĻèĵī
    0.21
    è¾°
    0.20
    æĻĹ
    0.20
    ä¸ĭè¡Į
    0.19
    åħ¨æĺİæĺŁ
    0.18
    ä¸Ńæŀ¢
    0.18
    è°ł
    0.18
    为代表çļĦ
    0.18
     Nobel
    0.18
    Activations Density 0.005%

    No Known Activations