© 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. 14533
    Prev
    Next
    INDEX
    Explanations

    underserved, marginalized, vulnerable groups

    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
    æ·±åĮĸæĶ¹éĿ©
    -0.20
    殿åłĤ
    -0.20
    ä¸įå®ļ
    -0.19
    建æĪIJåIJİ
    -0.19
    æ©IJ
    -0.18
    大åİħ
    -0.18
    大æĪĺ
    -0.18
     savedInstanceState
    -0.18
    ãģĬåĭ§ãĤģ
    -0.17
    é«ĺæ°´å¹³
    -0.17
    POSITIVE LOGITS
     areas
    0.23
    è§ĴèIJ½
    0.22
    åľ°ä½į
    0.22
     regions
    0.21
    åľ°åĮºçļĦ
    0.20
    éĺ¶å±Ĥ
    0.20
    é¢ĨåŁŁçļĦ
    0.20
    overn
    0.19
     bast
    0.19
    .Compute
    0.19
    Activations Density 0.016%

    No Known Activations