© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2739
    Prev
    Next
    INDEX
    Explanations

    real estate sale and selling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     Arb
    -0.25
    äºļ马
    -0.25
    æķijæĬ¤
    -0.24
    ä¸Ģä¼ļåĦ¿
    -0.23
     Laurent
    -0.23
    游çİ©
    -0.22
     corresponding
    -0.22
    æĬĬæĮģ
    -0.22
    è¡Į车
    -0.22
     Euler
    -0.22
    POSITIVE LOGITS
    款
    0.24
    pping
    0.24
    prep
    0.24
    warts
    0.23
    reh
    0.23
     dormant
    0.23
    aison
    0.23
    æĪ¿äº§
    0.23
    pped
    0.23
    cidade
    0.23
    Activations Density 0.013%

    No Known Activations