© 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. 19212
    Prev
    Next
    INDEX
    Explanations

    months followed by day numbers

    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
    åĮ®
    -0.10
    楼ä¸Ĭ
    -0.10
    (Cs
    -0.09
    é¹Ń
    -0.09
    èĶº
    -0.09
    èIJĮ
    -0.09
    ushman
    -0.08
    èĻ»
    -0.08
    anga
    -0.08
    _proto
    -0.08
    POSITIVE LOGITS
    ly
    0.10
    æĪijæł¡
    0.10
    åħļ
    0.09
    éĥĬ
    0.09
    饮æĸĻ
    0.08
    大ä¼Ĺ
    0.08
    èĻ¬
    0.08
    æĪijåĽ½
    0.07
    åºľ
    0.07
    APS
    0.07
    Activations Density 0.050%

    No Known Activations