© 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. 60881
    Prev
    Next
    INDEX
    Explanations

    colored and coloured descriptions

    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
    æĸ°åĬł
    -0.09
    омеÑĢ
    -0.09
    æ®ĸ
    -0.08
    oard
    -0.08
    çİ«
    -0.08
    å£ķ
    -0.08
    åĪĨ离
    -0.08
    agini
    -0.08
    责任åĪ¶
    -0.08
    èĻİ
    -0.08
    POSITIVE LOGITS
    æĻ°
    0.11
    çļĦåİĨåı²
    0.09
    幺
    0.09
    ãģ®ãģĮ
    0.09
     fuse
    0.09
    engo
    0.09
    ãģĤãģĴ
    0.08
    稿
    0.08
    à¹Ģà¸Ļ
    0.08
    brook
    0.08
    Activations Density 0.017%

    No Known Activations