© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14580
    Prev
    Next
    INDEX
    Explanations

    text alignment and centering

    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
    æĸĻ
    -0.21
     Surveillance
    -0.21
    éĵ²
    -0.20
    娣
    -0.19
    unik
    -0.19
    heed
    -0.18
    .bz
    -0.18
    è²·ãģĦçī©
    -0.18
    loom
    -0.18
    æľīèī²
    -0.18
    POSITIVE LOGITS
    -align
    0.21
    aling
    0.20
    mt
    0.20
     valign
    0.20
    åĪĹåħ¥
    0.19
     textAlign
    0.19
    æİĴåĪĹ
    0.19
    左边
    0.19
     direction
    0.19
    _float
    0.19
    Activations Density 0.145%

    No Known Activations