© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1204
    Prev
    Next
    INDEX
    Explanations

    lung cancer

    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
    -addons
    -0.24
     Nie
    -0.23
    Century
    -0.22
    -Dec
    -0.22
    mime
    -0.22
     lad
    -0.22
    avern
    -0.21
    天æīį
    -0.21
    inos
    -0.21
    aes
    -0.20
    POSITIVE LOGITS
    åIJĮæł·
    0.40
     albeit
    0.40
    çħ§æł·
    0.37
     вполне
    0.37
    åIJĮ樣
    0.35
     similarly
    0.34
     nonetheless
    0.32
     equally
    0.32
    ä¸Ģæł·
    0.31
    åIJĮæł·çļĦ
    0.31
    Activations Density 0.339%

    No Known Activations