© 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. 13346
    Prev
    Next
    INDEX
    Explanations

    narrative descriptions and storytelling

    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
    ç±ģ
    -0.21
    ened
    -0.21
    liness
    -0.18
    quam
    -0.18
     gái
    -0.18
    auce
    -0.18
    burgh
    -0.17
    áŁĴáŀ
    -0.16
    ération
    -0.16
    ify
    -0.16
    POSITIVE LOGITS
    ä¸įæ¸ħ
    0.21
    hip
    0.20
    æĢ§å¼º
    0.19
    æ»ļæ»ļ
    0.19
    ä¸ŃçļĦ
    0.18
     vitae
    0.18
    ative
    0.17
    IEL
    0.17
    weise
    0.17
    able
    0.16
    Activations Density 0.005%

    No Known Activations