© 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. 11180
    Prev
    Next
    INDEX
    Explanations

    life insurance, workshops, dates

    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
    mPid
    -0.20
    ulk
    -0.20
    æĸĩçĮ®
    -0.20
     Literature
    -0.19
     literature
    -0.19
    TECT
    -0.19
    äºĨæĪijçļĦ
    -0.18
    اÙħÙĬØ©
    -0.17
    èļĤ
    -0.17
    TickCount
    -0.17
    POSITIVE LOGITS
    å¹´ä¹ĭä¹ħ
    0.19
    chr
    0.18
    å¨ģå°Ķ
    0.18
    屿
    0.18
    Container
    0.18
    欤
    0.17
    entr
    0.17
    fabric
    0.17
    à¸Ńà¸Ńà¸ģ
    0.17
    ìĤ¬ìĿ´
    0.17
    Activations Density 1.008%

    No Known Activations