© 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. 14643
    Prev
    Next
    INDEX
    Explanations

    adding to lists or collections

    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
     saģlıkl
    -0.27
     wÅĤaÅĽ
    -0.25
     wÅĽ
    -0.25
     mükem
    -0.24
     knull
    -0.24
     miÄĻd
    -0.24
    schlü
    -0.22
    kaar
    -0.22
     uçu
    -0.21
    europäische
    -0.21
    POSITIVE LOGITS
    æĦıåij³
    0.20
    oval
    0.20
     diz
    0.19
    äºĨä¸Ģ个
    0.19
    of
    0.18
    à¹īà¸Ńà¸Ļ
    0.18
    åıªè§ģ
    0.18
    add
    0.18
    header
    0.17
    ç®Ĺæĺ¯
    0.17
    Activations Density 0.513%

    No Known Activations