© 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. 15853
    Prev
    Next
    INDEX
    Explanations

    quality

    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
    天æīį
    -0.22
    å¤©çľŁ
    -0.21
    çIJ¶
    -0.21
    çĶľèľľ
    -0.20
    åįĴ
    -0.20
    çĶľçĶľ
    -0.20
    çĻ½è¡£
    -0.19
    iais
    -0.19
    PORT
    -0.19
    æµİ
    -0.19
    POSITIVE LOGITS
     quality
    0.39
    è´¨éĩı
    0.39
    è´¨éĩıåĴĮ
    0.37
    çļĦè´¨éĩı
    0.34
    -quality
    0.32
    æĿIJè´¨
    0.32
    åĵģè´¨
    0.31
    質éĩı
    0.30
    quality
    0.30
    åģļå·¥
    0.30
    Activations Density 0.027%

    No Known Activations