© 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. 16381
    Prev
    Next
    INDEX
    Explanations

    languages and origins

    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
    åıĽ
    -0.22
    äºŃ
    -0.21
     Wired
    -0.19
    AtPath
    -0.19
     Beard
    -0.19
     khá»ı
    -0.19
    椽
    -0.19
    irs
    -0.18
    deaux
    -0.18
    大家åĪĨ享
    -0.18
    POSITIVE LOGITS
    æĦıæĢĿæĺ¯
    0.24
    iko
    0.22
    æĦıæĢĿ
    0.22
    è¯Ń
    0.20
     transl
    0.20
    ä¸įå¿ĺ
    0.20
    azo
    0.19
    驽
    0.19
    åĽ½åľŁ
    0.19
    ROT
    0.18
    Activations Density 0.061%

    No Known Activations