© 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. 13223
    Prev
    Next
    INDEX
    Explanations

    Continue reading

    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
    ikon
    -0.21
    çon
    -0.21
    ieg
    -0.20
    odu
    -0.20
    æŶéĹ´åĨħ
    -0.20
    DataContext
    -0.19
    erville
    -0.19
    otr
    -0.19
    ewire
    -0.18
    为ä¸Ģä½ĵ
    -0.18
    POSITIVE LOGITS
    大çĽĺ
    0.21
    åģļ个
    0.20
    è¿Ļåı¥è¯Ŀ
    0.18
    åįģä¹Ŀå±Ĭ
    0.18
    äºĭä¸ļåįķä½į
    0.18
     Bea
    0.18
    åı®
    0.18
    ä¸įè¿ĩ
    0.18
    被æĬĵ
    0.17
    tid
    0.17
    Activations Density 0.008%

    No Known Activations