© 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. 17312
    Prev
    Next
    INDEX
    Explanations

    Frontier or fortress

    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
    ete
    -0.19
    äºĴåĪ©
    -0.18
    lico
    -0.18
    åľĪ
    -0.18
    rg
    -0.17
    oval
    -0.16
    size
    -0.16
    soever
    -0.16
    äºĨä¸Ģåľº
    -0.15
     eslint
    -0.15
    POSITIVE LOGITS
    à¹Į
    0.20
    eturn
    0.18
    _LOADED
    0.18
    ÑģÑĤÑĮ
    0.17
    ä½Ĩè¿Ļ
    0.17
    ÑĢÑıд
    0.17
    .AWS
    0.17
    Į
    0.17
    çľģæĶ¿åºľ
    0.16
    ãģĮãĤī
    0.16
    Activations Density 0.002%

    No Known Activations