© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8524
    Prev
    Next
    INDEX
    Explanations

    opening quote or bracket, followed by text

    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
    pcl
    -0.09
    æĭīä¸ģ
    -0.09
    illus
    -0.09
    ars
    -0.08
    é£ŀæī¬
    -0.08
    à¹Į
    -0.08
    orz
    -0.08
    è¢ħ
    -0.08
    fur
    -0.08
    arParams
    -0.08
    POSITIVE LOGITS
    à¸Ļาà¸Ļ
    0.10
    ount
    0.09
     Booth
    0.09
    ÑĢез
    0.08
    æĪ¿ä¸ľ
    0.08
    ned
    0.08
    åĬ³åĬ¨èĢħ
    0.08
    æ¸
    0.08
    çĸ«æĥħ
    0.08
    ryo
    0.08
    Activations Density 0.085%

    No Known Activations