© 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. 12814
    Prev
    Next
    INDEX
    Explanations

    ordinal centuries

    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
    _capabilities
    -0.21
    éĢģæĿ¥
    -0.19
    çݰ代社ä¼ļ
    -0.19
     modern
    -0.19
    çĶľçĶľ
    -0.18
    å¾Ĺ天
    -0.18
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.18
    modern
    -0.18
    æ§Ľ
    -0.18
    [*
    -0.18
    POSITIVE LOGITS
    以åIJİ
    0.20
    åīįçŀ»æĢ§
    0.20
    æĹ¶æľŁ
    0.19
    usher
    0.19
    æŶåĢĻ
    0.19
    uish
    0.18
     onwards
    0.18
    é¦Ļæ°Ķ
    0.18
     обÑĭ
    0.18
     taxp
    0.18
    Activations Density 0.064%

    No Known Activations