© 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. 12256
    Prev
    Next
    INDEX
    Explanations

    Indian names and terms

    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
    .xhtml
    -0.24
    elves
    -0.22
    åħ¬æ°ij
    -0.21
    æ¹ĺ西
    -0.21
    社ä¼ļåĮĸ
    -0.20
    éĺ³åı°
    -0.20
    iếc
    -0.20
    åĤ©
    -0.20
    çĶij
    -0.19
     XHTML
    -0.19
    POSITIVE LOGITS
    çļĩå¸Ŀ
    0.22
     Indian
    0.21
    ultan
    0.21
    ستاÙĨ
    0.20
     Emperor
    0.20
    çİĭæľĿ
    0.20
    _orders
    0.20
    ây
    0.20
     dynasty
    0.19
     Islamic
    0.19
    Activations Density 0.057%

    No Known Activations