© 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. 15277
    Prev
    Next
    INDEX
    Explanations

    knighted or Knight associated phrases

    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
    ations
    -0.19
    æł·çļĦ
    -0.19
    ally
    -0.19
    ÑĤов
    -0.18
    .assertj
    -0.17
    ivity
    -0.17
    ation
    -0.17
    quier
    -0.17
    oven
    -0.16
    ator
    -0.16
    POSITIVE LOGITS
    /her
    0.17
    mare
    0.17
    -quarters
    0.17
    /from
    0.15
    åĪ©äºİ
    0.15
    ãģĦãĤĭãģ¨
    0.15
     Tear
    0.14
    ,:,
    0.14
    ł
    0.14
    «
    0.14
    Activations Density 0.093%

    No Known Activations