© 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. 14612
    Prev
    Next
    INDEX
    Explanations

    institutions and facilities

    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
    mant
    -0.19
    æĹ¥æĬ¥ç¤¾
    -0.18
    TextNode
    -0.18
    åĪ»èĭ¦
    -0.18
    æ¯Ķäºļ
    -0.18
    movies
    -0.18
    åģļ人
    -0.18
    æ¹ĸåĮº
    -0.18
    海滩
    -0.18
    çķľçī§
    -0.18
    POSITIVE LOGITS
    建设åĴĮ
    0.26
    管çIJĨåĴĮ
    0.25
    bau
    0.22
    们
    0.21
    hood
    0.20
    åįĩ级æĶ¹éĢł
    0.20
     management
    0.20
    ãģ¥ãģıãĤĬ
    0.19
    è¿IJä½ľ
    0.19
    建设
    0.19
    Activations Density 0.197%

    No Known Activations