© 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. 61276
    Prev
    Next
    INDEX
    Explanations

    biodiversity and species distribution

    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
    å®ļåIJij
    -0.10
    æĹº
    -0.10
    ç¥Ī祷
    -0.09
    Meteor
    -0.09
     Affero
    -0.09
    ç¥Ī
    -0.08
    æĿijæ°ij
    -0.08
    èIJ½åIJİ
    -0.08
    æŃ£å¸¸ä½¿çĶ¨
    -0.08
    渲
    -0.08
    POSITIVE LOGITS
    说æĺİ书
    0.09
    å±¥
    0.09
     Williamson
    0.09
    åĪĨ级
    0.09
    åī©ä¸ĭ
    0.09
    丰å¯ĮçļĦ
    0.08
    çİ°åŃĺ
    0.08
    orna
    0.08
    POSE
    0.08
    ToDevice
    0.08
    Activations Density 0.141%

    No Known Activations