© 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. 17094
    Prev
    Next
    INDEX
    Explanations

    solve

    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
    eras
    -0.18
    że
    -0.17
    valid
    -0.17
    ige
    -0.17
    åĽŀäºĭ
    -0.16
    rox
    -0.16
    oints
    -0.16
    red
    -0.15
    apolis
    -0.15
     cáºŃn
    -0.15
    POSITIVE LOGITS
    ä¸įäºĨ
    0.24
    bars
    0.21
    ä¹ĭéģĵ
    0.20
    åĬŀæ³ķ
    0.17
    itaire
    0.17
    ราà¸Ĭà¸ģาร
    0.17
    èĦ²
    0.16
    pek
    0.16
    ì±ħ
    0.16
    æĦł
    0.16
    Activations Density 0.043%

    No Known Activations