© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12486
    Prev
    Next
    INDEX
    Explanations

    apparatus, device, or article

    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
    ä¸į容
    -0.28
     поÑģколÑĮ
    -0.21
    æĦıåij³
    -0.21
    ÓĽ
    -0.21
    ENSE
    -0.20
    ä¸ĢæŦ
    -0.19
     минималÑĮн
    -0.19
    odiac
    -0.18
    á¿ij
    -0.18
    idot
    -0.18
    POSITIVE LOGITS
    æļ¾
    0.23
     име
    0.21
     Ñģвоими
    0.21
    ÑıÑĤ
    0.20
    _modes
    0.20
    为äºĨæĽ´å¥½
    0.20
    sus
    0.20
    æŁIJä¸Ģ
    0.19
    본
    0.19
    _real
    0.19
    Activations Density 0.973%

    No Known Activations