© 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. 61973
    Prev
    Next
    INDEX
    Explanations

    last time, day, or event

    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
    æѧ
    -0.09
     BH
    -0.09
    LIK
    -0.09
    é¦ĸä½į
    -0.08
    ibur
    -0.08
    社ä¼ļåĮĸ
    -0.08
    Elements
    -0.08
    ega
    -0.08
    é¦Ĩ
    -0.08
    EMU
    -0.08
    POSITIVE LOGITS
    ä»ĬçĶŁ
    0.10
    ä¼ı
    0.10
    ãģĹãģ°ãĤīãģı
    0.10
    è§ŀ
    0.09
    è¡·å¿ĥ
    0.09
    缴åĪ°
    0.09
     pedal
    0.09
    详解
    0.09
    åIJĮæĹ¶ä¹Łæĺ¯
    0.08
    .major
    0.08
    Activations Density 0.031%

    No Known Activations