© 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. 12430
    Prev
    Next
    INDEX
    Explanations

    abstract life concepts

    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
    sworth
    -0.19
    ä¸ĢåĽ¢
    -0.18
    íļį
    -0.18
    mate
    -0.18
    次ä¼ļè®®
    -0.17
     wre
    -0.17
    解å¼Ģ
    -0.17
    ooks
    -0.17
    PPER
    -0.17
     Saying
    -0.17
    POSITIVE LOGITS
    æ¯ıåij¨
    0.20
    ivic
    0.20
    haled
    0.20
     deb
    0.19
    ®
    0.18
    ä¹ħ
    0.18
    å¥ı
    0.18
    çļĦç¾İ好
    0.18
    esktop
    0.18
     Dol
    0.17
    Activations Density 0.003%

    No Known Activations