© 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. 11886
    Prev
    Next
    INDEX
    Explanations

    ..oil.fatty.gene.RNA.anti.bin.plasma.Hu.python

    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
    èįĩ
    -0.22
    zik
    -0.21
    é²ľ
    -0.20
    é®®
    -0.19
    borg
    -0.19
    orda
    -0.18
     INTERN
    -0.18
    osl
    -0.18
    èĤ¡
    -0.18
    èĥ´
    -0.17
    POSITIVE LOGITS
    ity
    0.21
    cele
    0.18
    级åĪ«
    0.18
    ä»Ģä¹Īéĥ½ä¸į
    0.18
    å¼ĺæī¬
    0.17
    æµħ
    0.17
    èĬĹ
    0.17
    éĻ¶
    0.17
    åºļ
    0.17
     noisy
    0.17
    Activations Density 0.001%

    No Known Activations