© 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. 14365
    Prev
    Next
    INDEX
    Explanations

    get from

    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
    orgot
    -0.20
    CumhurbaÅŁkan
    -0.20
    obia
    -0.20
    æķijæĬ¤
    -0.20
     geschichten
    -0.20
    #ae
    -0.20
    prowadzi
    -0.19
    æIJľçĭIJé¦ĸ页
    -0.19
    ofile
    -0.19
    æľī两ç§į
    -0.19
    POSITIVE LOGITS
     —
    0.23
    éĤ£ç§į
    0.21
    ä»Ĭ天å°ıç¼ĸ
    0.21
    对äºİæĪij们
    0.21
    ä¸įèĩ³äºİ
    0.20
    ä¸İæŶ
    0.20
     âĢ¦
    0.20
    ero
    0.19
     pit
    0.19
    ä¸įå°ij
    0.19
    Activations Density 1.464%

    No Known Activations