© 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. 11772
    Prev
    Next
    INDEX
    Explanations

    of that

    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
    ä¼łç»ŁçļĦ
    -0.24
    à¸Ħà¸ĵะà¸ģรรม
    -0.21
    åĽłä¸ºæĪij们
    -0.21
    åħ¹
    -0.20
    äºļ太
    -0.20
    ÂŃs
    -0.20
    à¸Ńำà¸Ļวยà¸Ħวาม
    -0.19
    ãĬĹ
    -0.19
     Tod
    -0.19
     traditional
    -0.19
    POSITIVE LOGITS
    æŁIJ
    0.31
    åı¦ä¸Ģ
    0.29
    该
    0.28
     each
    0.26
    æŁIJ个
    0.25
    each
    0.25
    æŁIJä¸Ģ
    0.25
     конкÑĢеÑĤ
    0.24
    該
    0.24
     íķ´ëĭ¹
    0.24
    Activations Density 0.348%

    No Known Activations