© 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. 22875
    Prev
    Next
    INDEX
    Explanations

    some

    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
    ä½łçľĭ
    -0.09
    è´¨çĸij
    -0.09
    asti
    -0.09
    irs
    -0.08
    èĨĽ
    -0.08
    ä¹ĥèĩ³
    -0.08
    åīįæīĢ
    -0.08
    [url
    -0.08
    éķ¿è¾¾
    -0.08
    æľ¬æĿ¥
    -0.08
    POSITIVE LOGITS
    ä¸ĢäºĽ
    0.29
    çļĦä¸ĢäºĽ
    0.28
    äºĽè®¸
    0.26
     some
    0.25
    äºĨä¸ĢäºĽ
    0.23
    æľīä¸ĢäºĽ
    0.23
    å°ij许
    0.22
    äºĽ
    0.21
     بعض
    0.21
     некоÑĤоÑĢÑĭÑħ
    0.21
    Activations Density 0.306%

    No Known Activations