© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21648
    Prev
    Next
    INDEX
    Explanations

    Saint Alban's

    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
    برÙĬ
    -0.09
    å·©
    -0.08
    æĭ©
    -0.08
     Maid
    -0.08
    flat
    -0.08
    апÑĢ
    -0.08
    EMS
    -0.08
    otal
    -0.08
    è¡Ĺéģĵ
    -0.08
    館
    -0.08
    POSITIVE LOGITS
    æģĤ
    0.10
    缸è¿ŀ
    0.09
    å°ijå¹´
    0.09
    建档
    0.09
    为人
    0.08
    kie
    0.08
    ç´«èī²
    0.08
     ëĦĺ
    0.08
    飧
    0.08
    asto
    0.08
    Activations Density 0.023%

    No Known Activations