© 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. 13519
    Prev
    Next
    INDEX
    Explanations

    email headers with slashes

    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
    æłĩè¯Ń
    -0.21
    ither
    -0.20
    æķĻèĤ²èµĦæºIJ
    -0.19
    /helper
    -0.18
     pamph
    -0.18
     appreciated
    -0.18
    å½ĵæĪij们
    -0.18
     Apprec
    -0.18
    edata
    -0.18
    å¹´ä¹ĭ
    -0.18
    POSITIVE LOGITS
    åĿ³
    0.22
     Bloomberg
    0.21
    缼
    0.20
    åīįçŀ»
    0.20
    ä½ľèĢħæľ¬äºº
    0.20
    èĥģ
    0.19
    çĨĬçĮ«
    0.19
    Editors
    0.19
    åĪĨæŀIJå¸Ī
    0.19
     tide
    0.19
    Activations Density 0.019%

    No Known Activations