© 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. 15531
    Prev
    Next
    INDEX
    Explanations

    Month names and numbers

    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
    èĨĿ
    -0.20
    ç»ĦåĽ¾
    -0.20
     Catal
    -0.20
     Vend
    -0.19
    episode
    -0.19
     overflow
    -0.18
    ä¼łéĢģ
    -0.18
    ﹩
    -0.18
    èĨĿçĽĸ
    -0.18
    Hom
    -0.18
    POSITIVE LOGITS
    æİıåĩº
    0.22
    çĶŁæķĪ
    0.22
    cljs
    0.20
    å±IJ
    0.20
    werk
    0.20
     wrestler
    0.20
    åĩıè½»
    0.19
    æı½
    0.19
     Rider
    0.19
    æĮĩå®ļ
    0.18
    Activations Density 0.073%

    No Known Activations