© 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. 15752
    Prev
    Next
    INDEX
    Explanations

    past tense verb endings

    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
    ity
    -0.28
    主ä¹ī
    -0.21
    gary
    -0.20
     ëıĻìĭľìĹIJ
    -0.18
    ëį°
    -0.18
    ä¸įæħİ
    -0.17
    主ä¹īèĢħ
    -0.16
    姥姥
    -0.16
    æĸ°å¨ĺ
    -0.16
    jective
    -0.15
    POSITIVE LOGITS
    ed
    1.05
    ly
    0.84
    edBy
    0.68
    äºĨ
    0.48
    ally
    0.47
    edb
    0.45
    ãģ¾ãģĹãģŁ
    0.43
    edList
    0.42
    äºĨæĪijçļĦ
    0.42
    edTextBox
    0.42
    Activations Density 1.769%

    No Known Activations