© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20171
    Prev
    Next
    INDEX
    Explanations

    botanical specimens or species

    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
    edom
    -0.11
    arine
    -0.10
     Че
    -0.09
    é¡
    -0.09
    èĽĭ
    -0.09
     Cunning
    -0.08
    è¿Ļåıª
    -0.08
    баÑĢ
    -0.08
    มาà¸Īาà¸ģ
    -0.08
    bose
    -0.08
    POSITIVE LOGITS
    丼
    0.11
    纸ä¸Ĭ
    0.10
     plants
    0.10
    èįı
    0.10
    çĿ¹
    0.10
    èĮĤ
    0.10
    ç¾ŀ
    0.10
    èĬ±èįī
    0.09
    å¼ĢèĬ±
    0.09
     grown
    0.09
    Activations Density 0.080%

    No Known Activations