© 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. 16447
    Prev
    Next
    INDEX
    Explanations

    for the benefit of

    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
    slick
    -0.19
    ocha
    -0.19
    äºĨä¸Ģéģį
    -0.19
    æļ´éĽ¨
    -0.19
    glob
    -0.19
    å¼·ãģĦ
    -0.18
    以人为
    -0.18
    posit
    -0.18
    mic
    -0.18
    ä¸Ģæ³¢
    -0.18
    POSITIVE LOGITS
     purposes
    0.31
     sake
    0.30
    广大
    0.25
    身å¿ĥåģ¥åº·
    0.24
     benefit
    0.22
    åıµ
    0.22
    缮çļĦ
    0.20
     purpose
    0.20
    广大群ä¼Ĺ
    0.20
    /classes
    0.20
    Activations Density 0.030%

    No Known Activations