© 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. 13670
    Prev
    Next
    INDEX
    Explanations

    street names and addresses

    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
     personal
    -0.22
    家å±ħ
    -0.21
    个人
    -0.20
     grat
    -0.20
    å¼±
    -0.19
     Houses
    -0.19
     pil
    -0.19
     prec
    -0.18
    æī¿
    -0.18
     h
    -0.18
    POSITIVE LOGITS
    åıĭè°Ĭ
    0.22
    å·¥ç¨ĭ建设
    0.22
    åıĺå¹»
    0.21
    åħ¬åħ±èµĦæºIJ
    0.21
    åħ¨ä½ĵåijĺå·¥
    0.21
    人æ°ijæľįåĬ¡
    0.20
    建æĪIJåIJİ
    0.20
    人éĢł
    0.20
    ipline
    0.20
     büyü
    0.20
    Activations Density 0.031%

    No Known Activations