© 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. 16878
    Prev
    Next
    INDEX
    Explanations

    São Paulo State

    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
    é¬ĵ
    -0.21
    岫
    -0.20
    山水
    -0.20
    æĥħæĢĢ
    -0.19
    ç»Ĵ
    -0.19
    ä¾Ľæļĸ
    -0.19
    嵩
    -0.18
    æ²³åĮĹçľģ
    -0.18
    éĺı
    -0.18
    è¹ļ
    -0.18
    POSITIVE LOGITS
    istan
    0.21
    etr
    0.20
    ety
    0.19
    å¸ĥ
    0.19
     buzz
    0.19
    buzz
    0.19
    etti
    0.18
    åľ¨ä¸Ĭæµ·
    0.18
    sky
    0.18
    san
    0.18
    Activations Density 0.009%

    No Known Activations