© 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. 11475
    Prev
    Next
    INDEX
    Explanations

    why should or would

    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
    åIJĦè¡Į
    -0.23
    åIJijåīį
    -0.21
    åħħåĪĨèĤ¯å®ļ
    -0.21
     доволÑĮно
    -0.20
    æľĢ常è§ģçļĦ
    -0.19
    大å±Ģ
    -0.19
    èµ·çłģ
    -0.18
    loud
    -0.18
    é«ĺå³°
    -0.18
    äºĨä¸įå°ij
    -0.18
    POSITIVE LOGITS
    çIJĨä¼ļ
    0.31
    æľīä»»ä½ķ
    0.30
     anything
    0.23
    åĩŃä»Ģä¹Ī
    0.23
    åľ¨æĦı
    0.22
     necessarily
    0.21
    ught
    0.21
     überhaupt
    0.21
     any
    0.21
    ä¼ļè§īå¾Ĺ
    0.21
    Activations Density 0.035%

    No Known Activations