© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14913
    Prev
    Next
    INDEX
    Explanations

    bad-ass design

    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
    è§Ĩ线
    -0.20
    gie
    -0.20
    ä¸Ŀä¸Ŀ
    -0.18
    èݳ
    -0.18
    èĪ«
    -0.17
    çĽĪ
    -0.17
    éĩijéĵ¶
    -0.17
     Jays
    -0.17
     avid
    -0.17
    viso
    -0.17
    POSITIVE LOGITS
    ounds
    0.20
    ery
    0.19
    ella
    0.19
    eren
    0.19
    åģļåĪ°äºĨ
    0.18
    建ç«ĭäºĨ
    0.18
    纵
    0.18
    ä¸ĸçķĮ第ä¸Ģ
    0.18
    åĦ¿
    0.18
    æ¦ľåįķ
    0.18
    Activations Density 0.003%

    No Known Activations