© 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. 16623
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    NBC
    -0.20
    æľ«
    -0.19
    èİ«
    -0.19
    chr
    -0.18
    åĪĨåĪ«æĺ¯
    -0.17
     اÙĦسÙĦØ·
    -0.17
    pix
    -0.17
    ore
    -0.17
    çļĦ好
    -0.17
    lo
    -0.17
    POSITIVE LOGITS
    .readString
    0.20
    çľ·
    0.19
    æŃ£æĸĩ
    0.19
    é¦Ĵ
    0.18
    erot
    0.18
    èĢģ人家
    0.18
    ness
    0.17
    çĪ±åĽ½ä¸»ä¹ī
    0.17
    .setTimeout
    0.17
    .byId
    0.17
    Activations Density 0.231%

    No Known Activations