© 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. 14474
    Prev
    Next
    INDEX
    Explanations

    months and free agency

    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
    æĬ½
    -0.20
    å¼ķæµģ
    -0.20
    plx
    -0.20
    åľ°éģĵ
    -0.20
    éļ¨æĻĤ
    -0.19
    _trigger
    -0.19
    çĽijæݧ
    -0.18
    Çģ
    -0.18
    alo
    -0.18
    åŀĤ
    -0.18
    POSITIVE LOGITS
    é¢Ħ
    0.27
    éłIJ
    0.21
    åģĩæľŁ
    0.21
     preparations
    0.21
    æıIJåīį
    0.20
    延伸
    0.20
    é¢ĦåĶ®
    0.20
    .ping
    0.20
     preparation
    0.20
    æĨ§æĨ¬
    0.20
    Activations Density 0.181%

    No Known Activations