© 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. 22844
    Prev
    Next
    INDEX
    Explanations

    instructions and calls to action

    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
    ä¿Ń
    -0.10
    elist
    -0.09
     ADV
    -0.08
     Grat
    -0.08
    iar
    -0.08
     ÐĽÑİ
    -0.08
    æ»ĵ
    -0.08
    agh
    -0.08
    æѤæĻĤ
    -0.08
     Wonderful
    -0.08
    POSITIVE LOGITS
    åģļåĪ°
    0.11
    大å±Ģ
    0.09
    æĮij
    0.09
    çĶļèĩ³
    0.09
    ä¹ŁåĽłæѤ
    0.09
    èĢĮä¸įæĺ¯
    0.09
    tra
    0.09
    Synopsis
    0.09
    è¨Ĺ
    0.09
    çĦ¶åIJİ
    0.09
    Activations Density 0.088%

    No Known Activations