© 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. 11839
    Prev
    Next
    INDEX
    Explanations

    starts at

    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
    Unnamed
    -0.21
     PaÅĦstwo
    -0.21
    缩
    -0.20
    ivable
    -0.20
    æľīæĽ´å¤ļçļĦ
    -0.20
    æĪĸå¤ļ
    -0.20
    OUS
    -0.19
    å«£
    -0.19
    失
    -0.18
     MessageLookup
    -0.18
    POSITIVE LOGITS
    ç¼¢
    0.21
    大éŨ
    0.19
    ç»ĨåĪĻ
    0.18
    å®īæİĴ
    0.18
    ç»Ĩå¾®
    0.18
    é¢Ħ
    0.18
    alking
    0.18
    æĭĽ
    0.17
    åħ¥åľº
    0.17
    ãģĻãģ¹ãģ¦
    0.17
    Activations Density 0.004%

    No Known Activations