© 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. 15745
    Prev
    Next
    INDEX
    Explanations

    home or house

    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
    çľ¼åīį
    -0.23
    èĭ«
    -0.21
    èµĦè´¨
    -0.20
    åŃĺåľ¨äºİ
    -0.19
    åĸĦæĦı
    -0.19
    icl
    -0.19
    æĦıåIJij
    -0.19
    åľ°çľĭçĿĢ
    -0.19
    ç¡®å®ļ
    -0.18
    天èµĭ
    -0.18
    POSITIVE LOGITS
    mates
    0.27
    åĨħçļĦ
    0.25
    -wide
    0.24
    çĶ¨åĵģ
    0.23
    éĩĮçļĦ
    0.23
    åĴĮ社ä¼ļ
    0.22
    /Home
    0.21
     ÑħозÑıй
    0.21
    onga
    0.21
    mate
    0.21
    Activations Density 0.049%

    No Known Activations