© 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. 14344
    Prev
    Next
    INDEX
    Explanations

    comment or say something

    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
    åIJ¼
    -0.21
     backpage
    -0.21
    å«ģç»Ļ
    -0.21
    æĹĸ
    -0.20
    Laugh
    -0.20
    ä»ĸä»¬åľ¨
    -0.20
    éĩİå¿ĥ
    -0.20
    ç¬ijäºĨ
    -0.19
    å©ļåIJİ
    -0.19
    æĥ³è¿ĩ
    -0.19
    POSITIVE LOGITS
    æŁIJç§į
    0.28
     somehow
    0.24
     something
    0.23
    åį³å°Ĩ
    0.22
    something
    0.22
    è¿Ļä¸ĢåĪ»
    0.21
    åĪļæīį
    0.20
    èŀį为ä¸Ģä½ĵ
    0.19
    æľ¬æ¬¡æ´»åĬ¨
    0.19
    è¿Ļä¸ªåľ°æĸ¹
    0.19
    Activations Density 0.042%

    No Known Activations