© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23571
    Prev
    Next
    INDEX
    Explanations

    weekend events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åĽĽåŃ£
    -0.09
    宿èĪį
    -0.09
    ä¸ľäº¬
    -0.09
    æµ®åĬ¨
    -0.09
     Fool
    -0.09
    é»ijæļĹ
    -0.09
    rss
    -0.08
    ibur
    -0.08
    ingle
    -0.08
     gre
    -0.08
    POSITIVE LOGITS
    åij¨æľ«
    0.15
     weekend
    0.14
     weekends
    0.10
     Saturday
    0.10
     Weekend
    0.09
    åij¨åħŃ
    0.09
    æĭĻ
    0.09
    رÙĪع
    0.09
    å¥īçĮ®
    0.09
    positories
    0.08
    Activations Density 0.069%

    No Known Activations