© 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. 2499
    Prev
    Next
    INDEX
    Explanations

    MHC antigen presentation

    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
    brook
    -0.10
    анÑģ
    -0.09
     ban
    -0.09
     Crazy
    -0.08
    Stretch
    -0.08
    çĶŁæ¶¯
    -0.08
    oppel
    -0.08
    åĪĨ离
    -0.08
    upil
    -0.08
    Camb
    -0.08
    POSITIVE LOGITS
    ç¡ĩ
    0.09
    å°ıåIJĥ
    0.09
    æĵį
    0.09
     lizard
    0.09
    ä¼łéĢĴ
    0.08
    ç¦Ģ
    0.08
    çĨ¨
    0.08
    ä¸ĵ线
    0.08
    èIJ¸
    0.08
    å²Ń
    0.08
    Activations Density 0.252%

    No Known Activations