© 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. 14627
    Prev
    Next
    INDEX
    Explanations

    detect or look for

    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
     mükem
    -0.23
     saģlıkl
    -0.22
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.22
    Cumhur
    -0.21
    á´Ĭ
    -0.21
    ogne
    -0.20
    mpp
    -0.20
     ünl
    -0.20
    åįķèģĮä¸ļ
    -0.19
    æµģåĬ¨
    -0.19
    POSITIVE LOGITS
    åĵķ
    0.23
    æݢ寻
    0.22
    æİ¢æµĭ
    0.21
    å°ĭ
    0.21
    åĢĮ
    0.21
    alist
    0.20
    é¹Ĭ
    0.20
    _MSG
    0.20
    寻æī¾
    0.20
    é¬ĵ
    0.20
    Activations Density 0.018%

    No Known Activations