© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14962
    Prev
    Next
    INDEX
    Explanations

    universities and institutes in place names

    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
     Ng
    -0.23
    对ä¼ģä¸ļ
    -0.21
    çĭ¬
    -0.20
     Cler
    -0.19
    对åħ¬åı¸
    -0.19
    Corporate
    -0.19
    åIJĦèĩª
    -0.19
    lers
    -0.19
    _COR
    -0.18
    ç¼Ĺ
    -0.18
    POSITIVE LOGITS
    å¼ıçļĦ
    0.24
    -era
    0.22
    åı·
    0.22
    ĽĦ
    0.21
    å¯Ĩçłģ
    0.21
    éĥħ
    0.21
    è¯ŀ
    0.21
    纪念é¦Ĩ
    0.20
    åħ¬åĽŃ
    0.20
    éĽķåĥı
    0.19
    Activations Density 0.061%

    No Known Activations