© 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. 12414
    Prev
    Next
    INDEX
    Explanations

    copyright, journal, retro, share

    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
    -caret
    -0.21
    ä¼İ
    -0.21
    åħ¥åĽŃ
    -0.21
    ä¿¡èµĸ
    -0.19
     ApplicationContext
    -0.19
    åĢ¾åIJij
    -0.19
    aras
    -0.19
    æīĭèĦļ
    -0.18
    .liferay
    -0.18
    为äºĨ让
    -0.18
    POSITIVE LOGITS
     margin
    0.22
    margin
    0.21
    omentum
    0.20
     margins
    0.20
    aly
    0.19
    .margin
    0.18
    ange
    0.18
    大夫
    0.18
    é£ĺ
    0.17
    çľĭæ¸ħ
    0.17
    Activations Density 0.001%

    No Known Activations