© 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. 48229
    Prev
    Next
    INDEX
    Explanations

    quantities related to measurement and distributions

    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
    wise
    -0.08
    é«ĺé¢Ŀ
    -0.08
    è¿ĩå¾Ĺ
    -0.08
    ward
    -0.08
    /generated
    -0.08
    asser
    -0.08
    ç¨Ģ
    -0.08
    ëį°
    -0.07
    å·²ä¹ħçļĦ
    -0.07
     temperament
    -0.07
    POSITIVE LOGITS
    åıĺåĮĸ
    0.12
    çļĦåıĺåĮĸ
    0.10
    éļı
    0.09
    è®ĬåĮĸ
    0.09
    ä¸ĩåįĥ
    0.09
    å®Ī
    0.09
    æģĻ
    0.09
     каждого
    0.09
    umer
    0.09
    æĦı大
    0.09
    Activations Density 1.172%

    No Known Activations