© 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. 14333
    Prev
    Next
    INDEX
    Explanations

    tutorials by Julie

    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
     civil
    -0.21
    itur
    -0.20
     gag
    -0.19
    èĥ½æºIJ
    -0.19
     ant
    -0.19
     recover
    -0.19
    .wikipedia
    -0.19
     foreign
    -0.18
     plays
    -0.18
    éģĤ
    -0.18
    POSITIVE LOGITS
    çļĦæķĻåѦ
    0.30
    讲å¸Ī
    0.30
    æĬĢæ³ķ
    0.29
    æİĪ课
    0.28
    æķĻåѦ
    0.27
    æķĻåŃ¦è´¨éĩı
    0.27
    è§Ĩé¢ij
    0.26
    åĭķä½ľ
    0.26
    å®ŀçĶ¨
    0.26
    æķĻç¨ĭ
    0.26
    Activations Density 0.048%

    No Known Activations