© 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. 12902
    Prev
    Next
    INDEX
    Explanations

    use permits

    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
    éĤ£æł·
    -0.23
    alto
    -0.21
    è¿Ļ件äºĭæĥħ
    -0.21
    alog
    -0.21
    æīĢè°ĵçļĦ
    -0.20
    éĵ¤
    -0.19
    è¿Ļæł·ä¸Ģ个
    -0.19
    Unnamed
    -0.19
    -mails
    -0.18
    è¿Ļ两ç§į
    -0.18
    POSITIVE LOGITS
    èĥ½åĬĽå¼º
    0.26
    éĻ¤å¤ĸ
    0.25
    åĭ¿
    0.21
    ä¹Łä¼ļ
    0.21
    åı¦æľī
    0.21
    ä¹Łæľī
    0.20
    亦
    0.20
    æĢ§å¼º
    0.20
    çĻ½è¡£
    0.19
    ãģĤãĤĬ
    0.19
    Activations Density 0.158%

    No Known Activations