© 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. 12549
    Prev
    Next
    INDEX
    Explanations

    edited by

    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
    nap
    -0.21
    æĥĬ人
    -0.18
    æ·³
    -0.18
    #line
    -0.18
    å¡ijéĢł
    -0.18
    thy
    -0.18
    à¹Ĥม
    -0.18
     @[
    -0.18
    tons
    -0.17
    éģģ
    -0.17
    POSITIVE LOGITS
    æ±ĩéĽĨ
    0.23
    	format
    0.20
    èĬ¦
    0.20
    _VEC
    0.19
    è¿Ļæľ¬ä¹¦
    0.19
     fiat
    0.19
    /compiler
    0.18
    cco
    0.18
    ç´Ĭ
    0.18
    sass
    0.18
    Activations Density 0.016%

    No Known Activations