© 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. 10338
    Prev
    Next
    INDEX
    Explanations

    punctuation following specific words

    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
    èĪĨ
    -0.21
    髦
    -0.21
     trusts
    -0.19
    .ua
    -0.19
    稽
    -0.18
    _lr
    -0.17
     EXIT
    -0.17
    ços
    -0.17
    idas
    -0.17
    -Za
    -0.17
    POSITIVE LOGITS
    山路
    0.22
    以éĺ²
    0.21
    çŃīåİŁåĽł
    0.21
    è¿ĻçĤ¹
    0.21
    containers
    0.20
    çŃīæĸ¹éĿ¢çļĦ
    0.20
    è¿ĻæĿ¡è·¯
    0.19
    ung
    0.19
    ritz
    0.19
    è°ģçŁ¥
    0.18
    Activations Density 0.120%

    No Known Activations