© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26176
    Prev
    Next
    INDEX
    Explanations

    names beginning with kenn

    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
    Negative Logits
    áĢĦ
    -0.09
    wel
    -0.09
    arily
    -0.09
    eos
    -0.09
    енÑĮк
    -0.08
    à¥į
    -0.08
    enko
    -0.08
    ter
    -0.08
    à¤Ī
    -0.08
    vent
    -0.08
    POSITIVE LOGITS
    åĴĮåľ°åĮº
    0.10
    人士
    0.10
    ilit
    0.10
    ials
    0.10
    ä¸įåIJĮç¨ĭ度
    0.10
    edly
    0.09
    ä¸Ģ个æĺ¯
    0.09
    çıij
    0.09
    theless
    0.09
    itter
    0.09
    Activations Density 0.014%

    No Known Activations