© 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. 12000
    Prev
    Next
    INDEX
    Explanations

    Slavic suffixes like icz/ski

    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
    å¼Ģä¼ļ
    -0.23
    æĹ¥åŃIJ
    -0.20
    èĽ
    -0.19
    ORA
    -0.19
    轧
    -0.19
    çļĦéĩį大
    -0.19
    å·®çĤ¹
    -0.19
    åĪĨæķ°
    -0.18
     ÐłÐµÑģп
    -0.18
    äºİ
    -0.18
    POSITIVE LOGITS
    ç»´å¥ĩ
    0.22
    icz
    0.20
     [[[
    0.20
    kus
    0.19
    Diamond
    0.19
    icum
    0.18
    ÄĹ
    0.18
     Hund
    0.18
    ices
    0.18
    æĤ¬å¿µ
    0.18
    Activations Density 0.046%

    No Known Activations