© 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. 4190
    Prev
    Next
    INDEX
    Explanations

    file names and locations

    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
    ãĥ¥
    -0.11
    åķª
    -0.09
    enis
    -0.09
    ãĤĩãģĨ
    -0.08
    è¿Ļæĺ¯ä¸Ģ个
    -0.08
    害
    -0.08
     nest
    -0.08
     поб
    -0.08
    urf
    -0.08
    از
    -0.08
    POSITIVE LOGITS
    迤
    0.10
    åıijçĶŁäºĨ
    0.09
    craft
    0.09
    èĭĵ
    0.09
    lectual
    0.09
     pine
    0.09
    iloc
    0.08
    诸
    0.08
    çİ°åĩº
    0.08
    对æĬĹ
    0.08
    Activations Density 0.010%

    No Known Activations