© 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. 16441
    Prev
    Next
    INDEX
    Explanations

    parties and events

    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
    ãĥŀãĥ¼
    -0.25
    çª
    -0.23
    ä¸ĩåħ¬éĩĮ
    -0.21
    èIJİ缩
    -0.21
    æĬ¥èĢĥ
    -0.21
    éĻIJãĤĬ
    -0.20
     backpage
    -0.20
    .IsNull
    -0.19
    æľĢæĸ°çļĦ
    -0.19
    ä¿®çĤ¼
    -0.19
    POSITIVE LOGITS
    æ¯ı人
    0.35
     guests
    0.34
    å¸ĥç½®
    0.30
     guest
    0.27
     everyone
    0.27
    åĺī宾
    0.27
    人人
    0.26
     Guests
    0.26
    客人
    0.26
    éģĵåħ·
    0.25
    Activations Density 0.026%

    No Known Activations