© 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. 33478
    Prev
    Next
    INDEX
    Explanations

    you will discover or see

    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
    .SizeType
    -0.11
    çīº
    -0.10
    adin
    -0.10
    家ä½ı
    -0.10
    mir
    -0.10
    stag
    -0.09
    ç»°
    -0.09
    ITES
    -0.09
    æłī
    -0.09
    riteln
    -0.09
    POSITIVE LOGITS
    人家
    0.09
    æŀ¢çº½
    0.08
    ../../../
    0.08
    elib
    0.08
    inea
    0.07
    .logs
    0.07
    Sort
    0.07
    èIJģ
    0.07
    âĦ¢
    0.07
     aver
    0.07
    Activations Density 0.053%

    No Known Activations