© 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. 12313
    Prev
    Next
    INDEX
    Explanations

    with an, with glass, with porcelain, with slab, with GPS

    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
    ngen
    -0.22
    æĺİæĺİ
    -0.21
    åħ¶å®ĥéĹ®é¢ĺ
    -0.19
     기íĥĢ
    -0.19
    nock
    -0.19
    usercontent
    -0.18
    ç»ĵå±Ģ
    -0.18
    åħĢ
    -0.18
    nst
    -0.17
    åħ¶ä»ĸçļĦ
    -0.17
    POSITIVE LOGITS
    éī´
    0.23
    aldi
    0.23
     dra
    0.20
    aul
    0.20
    åľ°æĸ¹
    0.18
    pd
    0.18
    mos
    0.18
    oned
    0.18
    å¤ļå±Ĥ次
    0.18
    涵çĽĸ
    0.18
    Activations Density 0.318%

    No Known Activations