© 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. 1470
    Prev
    Next
    INDEX
    Explanations

    place names and abbreviations

    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
    åŀ®
    -0.10
    çĪ¹
    -0.09
    åĸľæ¬¢åIJĥ
    -0.09
    dam
    -0.08
     dam
    -0.08
    .instances
    -0.08
    èѬ
    -0.08
     hose
    -0.08
    产ä¸ļåŁºåľ°
    -0.08
    ammers
    -0.08
    POSITIVE LOGITS
    累累
    0.09
    ÙĬرا
    0.09
    è´¢
    0.09
     çek
    0.09
    OLE
    0.08
    èħIJ
    0.08
    èĴĻ
    0.08
    ç§Ģ丽
    0.08
    çıĬçijļ
    0.08
    秤
    0.08
    Activations Density 0.050%

    No Known Activations