© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12410
    Prev
    Next
    INDEX
    Explanations

    reb, rebound, rebut

    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
    ../
    -0.19
    most
    -0.17
    éī´åĪ«
    -0.17
    pieces
    -0.16
    ÙħÙĨاز
    -0.16
    spell
    -0.16
    ãģĦãģ¾ãģĽãĤĵ
    -0.16
     habil
    -0.16
    ãģĦãĤĭ
    -0.16
    ured
    -0.15
    POSITIVE LOGITS
    åĪ¶åº¦
    0.21
    åIJĦç§į
    0.18
    ensburg
    0.17
    æľºä¼ļ
    0.17
    æĪIJåĬŁ
    0.17
    çİĩ为
    0.17
    eps
    0.16
    çİĩ
    0.16
    ambre
    0.16
    å½¢å¼ı
    0.16
    Activations Density 0.002%

    No Known Activations