© 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. 15443
    Prev
    Next
    INDEX
    Explanations

    claims that, million project, functioning prototype, -year-old, a new, aims to

    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
    åľ¨çݩ家ä¸Ń
    -0.31
     пÑĢиÑıÑĤн
    -0.29
     mükem
    -0.26
    sının
    -0.26
    åįķèģĮä¸ļ
    -0.24
     saģlıkl
    -0.24
     наÑĢко
    -0.24
    æĪĺç»ĦåIJĪ
    -0.24
    ãĤŃãĥ£ãĥ³ãĥļ
    -0.23
     overposting
    -0.23
    POSITIVE LOGITS
    éģĵåħ·
    0.25
    åİŁåŀĭ
    0.24
    趣åij³
    0.24
    ta
    0.24
    YouTube
    0.23
     reportedly
    0.23
    åIJ¬èµ·æĿ¥
    0.23
    ä¸ĵéŨ
    0.22
    æį£
    0.22
     fun
    0.22
    Activations Density 0.205%

    No Known Activations