© 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. 16004
    Prev
    Next
    INDEX
    Explanations

    how something is decided

    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
    éĩįçĤ¹é¢ĨåŁŁ
    -0.19
    notations
    -0.19
    çĸ½
    -0.18
    çĶŁæ´»ä¹łæĥ¯
    -0.18
    æŃ£åľ¨è¿Ľè¡Į
    -0.18
    جÙĩ
    -0.18
    ç»·
    -0.17
    .cg
    -0.17
    initialize
    -0.17
    nc
    -0.17
    POSITIVE LOGITS
    åĨ³å®ļ
    0.31
    åĪ¤å®ļ
    0.28
    åĪ¤æĸŃ
    0.27
     deciding
    0.26
    決å®ļ
    0.26
     decides
    0.26
    æĿĥ
    0.25
    éħĮ
    0.25
    认å®ļ
    0.25
    åĨ³å®ļäºĨ
    0.24
    Activations Density 0.038%

    No Known Activations