© 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. 26391
    Prev
    Next
    INDEX
    Explanations

    implantable medical devices

    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
    oola
    -0.10
    è¾ķ
    -0.09
    vor
    -0.09
    çĤİçĥŃ
    -0.09
    .opens
    -0.09
    lix
    -0.09
    è§Ĥèµı
    -0.09
     scraper
    -0.09
    yen
    -0.09
    ä¸Ńå¼ı
    -0.08
    POSITIVE LOGITS
    åĮ»çĸĹåĻ¨æ¢°
    0.15
    åĻ¨æ¢°
    0.12
    åĪ¶éĢł
    0.10
    åĮ»çĸĹæľºæŀĦ
    0.10
    械
    0.10
    å¾®åĪĽ
    0.10
    icals
    0.09
    製
    0.09
    .fhir
    0.09
    åĪ¶æĪIJ
    0.09
    Activations Density 0.591%

    No Known Activations