© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16788
    Prev
    Next
    INDEX
    Explanations

    metabolic syndrome and disorders

    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
    ness
    -0.18
    emente
    -0.18
    ifiable
    -0.17
    ksam
    -0.17
    OrElse
    -0.17
    åĥļ
    -0.17
    ä¸Ŀ绸
    -0.17
    SelectionMode
    -0.17
    ampa
    -0.16
    airo
    -0.16
    POSITIVE LOGITS
    æĹºçĽĽ
    0.21
    亢
    0.17
    .removeItem
    0.17
    -wise
    0.16
    ç´Ĭä¹±
    0.16
    emia
    0.16
    ic
    0.16
    t
    0.15
    è¡·
    0.15
     fluoride
    0.15
    Activations Density 0.028%

    No Known Activations