© 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. 14069
    Prev
    Next
    INDEX
    Explanations

    process or module

    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
    çĶŁæ¶¯
    -0.23
     Fib
    -0.21
     schw
    -0.21
     trans
    -0.20
     Mel
    -0.20
    hä
    -0.20
     Raz
    -0.19
     exile
    -0.19
     gang
    -0.19
     disse
    -0.19
    POSITIVE LOGITS
    让æ¶Īè´¹èĢħ
    0.29
     авÑĤо
    0.24
     MyBase
    0.24
     Erotische
    0.22
    å¸®ä½ł
    0.22
    æľīåĬ©
    0.22
    à¹Ĥà¸Ľà¸£à¹ģ
    0.21
     onAnimation
    0.21
    å¤ļè¾¾
    0.21
    樯
    0.20
    Activations Density 0.031%

    No Known Activations