© 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. 27935
    Prev
    Next
    INDEX
    Explanations

    long durations of time

    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
    å¤Ń
    -0.10
    itoris
    -0.09
    iben
    -0.09
    до
    -0.09
    unga
    -0.09
    å¾·æĭī
    -0.08
     ObjectOutputStream
    -0.08
    æ·¡åĮĸ
    -0.08
    berger
    -0.08
     Lives
    -0.08
    POSITIVE LOGITS
    çģ°å°ĺ
    0.09
    ä»ĭåħ¥
    0.09
    æĹħ客
    0.09
    ente
    0.09
    çļĦæŶåĢĻ
    0.09
    æ±Ĺ
    0.09
    ä¼¼çļĦ
    0.08
    é¦Ļèıĩ
    0.08
    ette
    0.08
    DITION
    0.08
    Activations Density 0.019%

    No Known Activations