© 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. 13699
    Prev
    Next
    INDEX
    Explanations

    thinking about actions, lessons, or questions

    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
    conf
    -0.22
    人éĢł
    -0.20
    CONF
    -0.19
    å¾ģæ±Ĥ
    -0.19
    Conf
    -0.19
    ä¸īåĽĽ
    -0.19
    å®ĺ宣
    -0.19
    breaker
    -0.19
     newText
    -0.19
    æIJŀå®ļ
    -0.18
    POSITIVE LOGITS
    æĢĿèĢĥ
    0.34
    åıįæĢĿ
    0.32
    æıIJéĨĴ
    0.31
    åIJ¯ç¤º
    0.29
    èŃ¦ç¤º
    0.29
    åıįçľģ
    0.26
    æĢĿç´¢
    0.25
    对çħ§
    0.24
    éŀŃ
    0.24
     rethink
    0.23
    Activations Density 0.044%

    No Known Activations