© 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. 13377
    Prev
    Next
    INDEX
    Explanations

    cut, section, harvest, resect

    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
    çĭİ
    -0.22
     Sector
    -0.22
    YE
    -0.20
    rolls
    -0.20
    å¸Į
    -0.19
    -sector
    -0.19
    åħ±äº«
    -0.19
    ãi
    -0.19
    æł¼å¤ĸ
    -0.19
     оÑĤлиÑĩа
    -0.19
    POSITIVE LOGITS
    éľ²åĩº
    0.26
    cut
    0.26
    Ĥ¬
    0.24
    åĪĩæĸŃ
    0.23
    Cut
    0.22
    åīª
    0.22
    åİ»æİī
    0.22
    顶éĥ¨
    0.21
    ä¸ĢåĪĢ
    0.21
     cutting
    0.20
    Activations Density 0.016%

    No Known Activations