© 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. 21812
    Prev
    Next
    INDEX
    Explanations

    social fabric and its components

    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
    ernaut
    -0.11
    terminal
    -0.10
    Terminal
    -0.10
     Terminal
    -0.10
    æħ§
    -0.09
     Berger
    -0.09
     Bathroom
    -0.09
    æĹłäºº
    -0.09
     позв
    -0.09
    mans
    -0.09
    POSITIVE LOGITS
    社交
    0.10
    è¯ļä¿¡
    0.10
    åķĦ
    0.10
    社ä¼ļèµĦæľ¬
    0.10
    éĤ»éĩĮ
    0.10
    社åĮº
    0.09
    ä¹¡åľŁ
    0.09
    ivic
    0.09
    æĸĩåĮĸåĴĮ
    0.09
    å®ŀä½ĵ
    0.09
    Activations Density 0.103%

    No Known Activations