© 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. 15599
    Prev
    Next
    INDEX
    Explanations

    special characters and separators

    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
    ris
    -0.25
    edly
    -0.22
    lix
    -0.21
    ourd
    -0.21
     ris
    -0.20
     Ris
    -0.20
     '
    -0.20
    uran
    -0.19
    umba
    -0.19
    èİ·å¾Ĺ
    -0.19
    POSITIVE LOGITS
    åľ°ä¸Ń
    0.21
    à¹Į
    0.19
    éĥ¨ä¸»ä»»
    0.19
    éķĤ
    0.19
    å§Ķ书记
    0.19
    è¡·å¿ĥ
    0.18
    æ»´
    0.18
    å°±æĺ¯åĽłä¸º
    0.18
    çŀ³
    0.18
    ping
    0.18
    Activations Density 0.056%

    No Known Activations