© 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. 16969
    Prev
    Next
    INDEX
    Explanations

    writing articles

    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
    èīºäºº
    -0.23
     Instagram
    -0.20
    apur
    -0.20
    atel
    -0.20
    åĵĪåĵĪåĵĪ
    -0.19
    éĹ¼
    -0.19
    arte
    -0.19
    åĵĪåĵĪåĵĪåĵĪ
    -0.19
     instagram
    -0.19
    ofi
    -0.19
    POSITIVE LOGITS
    åĪĬçĻ»
    0.27
     article
    0.24
     columnist
    0.23
    âİĻ
    0.22
     ÑģÑĤаÑĤÑĮ
    0.22
    åĶĨ
    0.21
    åıij表äºĨ
    0.21
    getColumn
    0.20
     enthus
    0.20
    æĸĩç«ł
    0.20
    Activations Density 0.081%

    No Known Activations