© 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. 10930
    Prev
    Next
    INDEX
    Explanations

    size and fit

    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
    etas
    -0.20
    æĢĢæĬ±
    -0.20
    箬
    -0.19
    è¿ĻæĿ¡
    -0.18
    .MouseDown
    -0.18
    vir
    -0.18
    _processing
    -0.18
     дал
    -0.18
    ìķĮ
    -0.17
    æĪij们认为
    -0.17
    POSITIVE LOGITS
    æŃ£ç¡®
    0.27
    åIJĪéĢĤ
    0.26
    æī¿
    0.24
     correct
    0.22
    åĩĨç¡®
    0.22
    æŃ£ç¡®çļĦ
    0.21
     correctly
    0.21
    æŃ£ç¢º
    0.21
    åģıå·®
    0.21
     appropri
    0.21
    Activations Density 0.028%

    No Known Activations