© 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. 11834
    Prev
    Next
    INDEX
    Explanations

    just, only, least, given, my

    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
    èĩªçĦ¶èĢĮ
    -0.23
    横
    -0.22
    VA
    -0.20
    ä½ıæīĢ
    -0.20
    library
    -0.20
    ÑĥÑĢ
    -0.19
    æĶ¯
    -0.19
    è¿Ļæĺ¯åĽłä¸º
    -0.19
    é¡¿æŶ
    -0.19
    processed
    -0.19
    POSITIVE LOGITS
    @dynamic
    0.30
    	RTLR
    0.26
    	RTLU
    0.26
     NUITKA
    0.23
    numerusform
    0.22
    JSGlobalScope
    0.22
    ÙħÙĨتدÙĬات
    0.21
    PropertyParams
    0.21
    å°Ĩ继ç»Ń
    0.21
    $fdata
    0.21
    Activations Density 0.046%

    No Known Activations