© 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. 13219
    Prev
    Next
    INDEX
    Explanations

    translation type

    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
     Tul
    -0.21
    ä»ĸ对
    -0.20
    lew
    -0.19
     Beard
    -0.19
    åŁº
    -0.19
    污
    -0.19
    oth
    -0.19
    ä¸Ń
    -0.19
    å®Į
    -0.18
     numbered
    -0.18
    POSITIVE LOGITS
    æĺ¯æ²¡æľī
    0.22
    积æŀģåĵįåºĶ
    0.21
     Olympia
    0.21
    éĩijå±±
    0.20
    ä¸Ģåij³
    0.20
    æ·º
    0.19
    ras
    0.19
    cas
    0.19
    åĽŀåºĶ
    0.19
    æĪĮ
    0.18
    Activations Density 0.006%

    No Known Activations