© 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. 14006
    Prev
    Next
    INDEX
    Explanations

    academic exams and preparation

    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
    åĢĴéĹŃ
    -0.22
    æŁĶ软
    -0.21
    åįķèģĮä¸ļ
    -0.20
    èĪĨ
    -0.20
    游æĪı代
    -0.20
    è¯Ħè®®
    -0.20
    责任å¿ĥ
    -0.19
    AMED
    -0.19
    =out
    -0.19
    游æĪıåī¯æľ¬
    -0.19
    POSITIVE LOGITS
    æĬĢå·§
    0.29
    æĶ»çķ¥
    0.23
    åıĭ
    0.23
    梳
    0.23
    åĨ²åĪº
    0.22
    奴
    0.22
    ä¸įåIJĥ
    0.21
    flu
    0.21
    éĢĨè¢Ń
    0.21
    åıĭ们
    0.21
    Activations Density 0.024%

    No Known Activations