© 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. 37284
    Prev
    Next
    INDEX
    Explanations

    list comprehension and iterators

    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
    ÐIJÐŀ
    -0.09
    ruptions
    -0.09
    epar
    -0.08
    ä¸İä¸ŃåĽ½
    -0.08
    plan
    -0.08
    pository
    -0.08
    对ä¸ŃåĽ½
    -0.08
    åħ³äºİ
    -0.07
    ior
    -0.07
    èĩ³å°ij
    -0.07
    POSITIVE LOGITS
    æŁIJä¸Ģ
    0.21
    æŁIJ
    0.21
    æŁIJ个
    0.20
    æŁIJç§į
    0.19
     or
    0.14
    æŁIJæŁIJ
    0.13
    æŁIJäºĽ
    0.12
     Certain
    0.11
    æĪĸ
    0.11
    หร
    0.11
    Activations Density 0.691%

    No Known Activations