© 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. 15412
    Prev
    Next
    INDEX
    Explanations

    joint ventures, partnerships, licensing agreements

    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
    åħ¬åĬ¡åijĺ
    -0.21
    个ä½ĵ
    -0.20
     finely
    -0.19
    ç¦ıçī¹
    -0.19
    对åħ¶çľŁå®ŀ
    -0.19
    å¯ĨéĽĨ
    -0.19
     обÑĢаÑī
    -0.18
    å¤ļä¹Ī
    -0.18
    ç¿ł
    -0.18
    è¡Ģç³ĸ
    -0.18
    POSITIVE LOGITS
    ä¸Ģæĸ¹
    0.22
    tees
    0.22
    legg
    0.21
    æ¯Ķä¾ĭ
    0.21
    æ¯į
    0.20
    åIJĦæĸ¹
    0.19
    utos
    0.19
     rÃłng
    0.19
    presso
    0.19
    è¾¾æĪIJ
    0.19
    Activations Density 0.019%

    No Known Activations