© 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. 1570
    Prev
    Next
    INDEX
    Explanations

    medical prescription

    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
     trò
    -0.19
    aroo
    -0.18
    å©¿
    -0.18
     invested
    -0.18
     immensely
    -0.18
     ------------------------------------------------------------------------↵
    -0.17
    _registered
    -0.17
    iken
    -0.17
    羣çļ®
    -0.17
    itarian
    -0.16
    POSITIVE LOGITS
    ï¬ĥ
    0.23
    /pre
    0.22
    eur
    0.21
    lius
    0.21
    ursive
    0.21
    /import
    0.21
    ments
    0.21
    dio
    0.19
    undle
    0.19
    paration
    0.19
    Activations Density 0.007%

    No Known Activations