© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7844
    Prev
    Next
    INDEX
    Explanations

    qualifications and credentials

    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
    ulton
    -0.10
    éªĢ
    -0.10
    ennen
    -0.09
    osten
    -0.09
    licable
    -0.09
    åŀ©
    -0.08
     Romero
    -0.08
    OCKET
    -0.08
    iser
    -0.08
    å¸Į
    -0.08
    POSITIVE LOGITS
    ä»ĬçĶŁ
    0.09
    楯
    0.09
     (*((
    0.09
    çľĭäºĨä¸Ģ
    0.08
    é¹°
    0.08
     ÑĥÑĩаÑģÑĤ
    0.08
    å¿ĺ
    0.08
     Hunters
    0.08
    æĢİä¹Īçľĭ
    0.08
    丫
    0.08
    Activations Density 0.026%

    No Known Activations