© 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. 14027
    Prev
    Next
    INDEX
    Explanations

    business partners

    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
    æĮijæĪĺ
    -0.19
    å®Įåħ¨
    -0.19
     Atl
    -0.19
     Hubb
    -0.18
    ä¸ĢåĪĨ
    -0.18
    ç®Ģ
    -0.18
     sce
    -0.18
    èĦ±
    -0.17
     Boxes
    -0.17
    /e
    -0.17
    POSITIVE LOGITS
    æģķ
    0.22
    èĬ±å¼Ģ
    0.20
    å¢ĥå¤ĸ
    0.19
    æĶĺ
    0.19
    æĤ²åĵĢ
    0.19
    åºĸ
    0.19
    badge
    0.18
    诸å¦Ĥ
    0.18
    åĽ½å¤ĸ
    0.18
    exus
    0.18
    Activations Density 0.017%

    No Known Activations