© 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. 59121
    Prev
    Next
    INDEX
    Explanations

    outdoor spaces

    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
    棹
    -0.11
    ingle
    -0.10
    身边
    -0.09
    rix
    -0.09
    身边çļĦ
    -0.09
    åĻ¨
    -0.09
    绩
    -0.09
     parte
    -0.09
    ners
    -0.09
    AFP
    -0.08
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.11
    паÑĢ
    0.09
    jen
    0.09
    ãģĮãĤī
    0.09
     Rosenstein
    0.09
    eenth
    0.09
    ľ
    0.09
    å¨ħ
    0.09
    รà¸Ńย
    0.09
     Verm
    0.09
    Activations Density 0.008%

    No Known Activations