© 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. 13957
    Prev
    Next
    INDEX
    Explanations

    sequence following numbers or punctuation

    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
    ÑĤол
    -0.19
    åħĪè¿Ľ
    -0.18
     ench
    -0.18
    .Raise
    -0.17
    æ±ł
    -0.17
    é¹ħ
    -0.17
    蹬
    -0.17
    .populate
    -0.17
     imb
    -0.17
    çľĭ
    -0.17
    POSITIVE LOGITS
    èµ¢å¾ĹäºĨ
    0.20
    rica
    0.19
    ä¸Ģç«Ļ
    0.19
    åºĦ严
    0.18
    rott
    0.18
    _FM
    0.18
    ãģĦãģıãĤī
    0.18
    âĨĹ
    0.17
    itations
    0.17
    å¤ľéĹ´
    0.17
    Activations Density 1.491%

    No Known Activations