© 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. 17245
    Prev
    Next
    INDEX
    Explanations

    sequences of characters including punctuation

    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
     particular
    -0.23
     pr
    -0.22
    ig
    -0.21
    ä¹Ł
    -0.21
    me
    -0.21
     lun
    -0.20
     firm
    -0.20
    cy
    -0.20
    åĪĻ
    -0.20
     ver
    -0.20
    POSITIVE LOGITS
    åºĶçĶ¨æŁ¥çľĭ
    0.23
     nuru
    0.23
    _sink
    0.23
     pornô
    0.22
    è¿Ļä¸ªåľ°åĽ¾
    0.22
    èĪĮå°ĸ
    0.22
    ernetes
    0.22
    sión
    0.22
     follando
    0.21
    æīĢæľīæĥħèĬĤ
    0.21
    Activations Density 0.040%

    No Known Activations