© 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. 14046
    Prev
    Next
    INDEX
    Explanations

    crowdsourcing/volunteers/code/compounds

    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
    æĢ»ä»·
    -0.21
    é«ĺæĸ°
    -0.21
    uros
    -0.20
     Coach
    -0.20
    ishments
    -0.20
    çŃĸåĪĴ
    -0.20
    Coach
    -0.19
    ued
    -0.19
    æĸ°ä¸ļæĢģ
    -0.19
    ãĥªãĥ¼
    -0.19
    POSITIVE LOGITS
    åħ¬æ°ij
    0.27
    å¿ĹæĦ¿èĢħ
    0.24
     volunteers
    0.22
     volunteer
    0.21
    å¿Ļç¢Į
    0.21
     citizen
    0.21
    å¿ĹæĦ¿
    0.21
    ä»»ä½ķ人éĥ½
    0.21
    Cit
    0.21
    ç§ijæĻ®
    0.21
    Activations Density 0.027%

    No Known Activations