© 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. 10672
    Prev
    Next
    INDEX
    Explanations

    XML schema definitions and types

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĭĭ
    -0.20
    çªĿ
    -0.19
    亢
    -0.19
     lam
    -0.19
    æ·¡
    -0.19
    inté
    -0.18
    Church
    -0.18
    .GetText
    -0.18
    door
    -0.18
    _LAT
    -0.18
    POSITIVE LOGITS
    æııè¿°
    0.29
    约æĿŁ
    0.26
     specification
    0.23
     schema
    0.23
    声æĺİ
    0.23
     specifications
    0.23
    è§Ħæł¼
    0.22
     description
    0.22
    èĩªå¾ĭ
    0.22
    Mismatch
    0.21
    Activations Density 1.051%

    No Known Activations