© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10321
    Prev
    Next
    INDEX
    Explanations

    reported speech verbs

    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
    Negative Logits
    åĴĮæľįåĬ¡
    -0.20
    è¿Ļ两ç§į
    -0.20
    åĴĮåľ°åĮº
    -0.20
    两ç§į
    -0.19
    çī¹åĪ«æĺ¯
    -0.18
    itere
    -0.17
     taraf
    -0.17
    éĵİ
    -0.17
    约为
    -0.17
    é¾Ľ
    -0.17
    POSITIVE LOGITS
    ä¸Ģåı¥
    0.22
    <Q
    0.19
    è¿Ļåı¥è¯Ŀ
    0.18
    ä¸Ģåı¥è¯Ŀ
    0.18
     after
    0.18
    说çĿĢ
    0.18
    Commerce
    0.18
    pres
    0.18
    åı£æ°Ķ
    0.18
    éĢģç»Ļ
    0.18
    Activations Density 0.032%

    No Known Activations