© 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. 15906
    Prev
    Next
    INDEX
    Explanations

    quantities of large numbers

    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
    AndWait
    -0.20
    ajo
    -0.19
    ÃŃo
    -0.19
    帮åĬ©
    -0.19
    itta
    -0.19
     aÄŁ
    -0.18
    ãģ¨ãģ«ãģĭ
    -0.18
     Leban
    -0.18
    itest
    -0.18
    ä¹Łæĺ¯ä¸Ģç§į
    -0.18
    POSITIVE LOGITS
    çĶļèĩ³
    0.27
    ä¹ĥèĩ³
    0.26
    åĩłåįģ
    0.26
    çĶļèĩ³æĺ¯
    0.25
     hundreds
    0.25
    åĩłçĻ¾
    0.25
     dozens
    0.23
    æķ°åįĥ
    0.22
     thousands
    0.21
    æķ°çĻ¾
    0.21
    Activations Density 0.054%

    No Known Activations