© 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. 13832
    Prev
    Next
    INDEX
    Explanations

    join our community

    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
    åĵī
    -0.20
     lẫn
    -0.18
    åīįä¸īåŃ£åº¦
    -0.18
    累累
    -0.18
    为ä½ķ
    -0.17
    _hello
    -0.17
    åĩºå¤Ħ
    -0.17
    åľ¨æķ´ä¸ª
    -0.17
     Crosby
    -0.17
    æĬķèµĦé¢Ŀ
    -0.17
    POSITIVE LOGITS
    社群
    0.20
    è¡ĮåĪĹ
    0.20
     ByteArray
    0.19
    æĸ°çļĦä¸Ģ
    0.19
    avigator
    0.18
    acky
    0.18
     society
    0.17
    _defs
    0.17
    SEQ
    0.17
    并éĢļè¿ĩ
    0.16
    Activations Density 0.019%

    No Known Activations