© 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. 16917
    Prev
    Next
    INDEX
    Explanations

    writer and screenwriter

    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
    å±ķåĵģ
    -0.22
    леп
    -0.20
    è¯ļ
    -0.19
     bir
    -0.19
    绣
    -0.18
    åį°è±¡
    -0.18
    åħ³æ³¨åº¦
    -0.18
    对åѦçĶŁ
    -0.18
    swick
    -0.18
    å±ķé¦Ĩ
    -0.18
    POSITIVE LOGITS
    çıŃåŃIJ
    0.21
    åī§æľ¬
    0.21
    ue
    0.21
    Frozen
    0.19
     McDon
    0.19
    ÐľÐŀ
    0.19
    atorial
    0.19
    ØŃØ©
    0.18
    ural
    0.18
    åij½ä¸Ń
    0.18
    Activations Density 0.019%

    No Known Activations