© 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. 51460
    Prev
    Next
    INDEX
    Explanations

    after a period of time

    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
    ä¸Ģä¸ĸ
    -0.11
    æĸ¹éĿ¢çļĦ
    -0.10
    èĮĥåĽ´åĨħ
    -0.10
    akest
    -0.10
    éĿŀ常好çļĦ
    -0.10
    å°ıäºĭ
    -0.09
    äºĮåŃĹ
    -0.09
    utely
    -0.09
    éħIJ
    -0.09
    abis
    -0.09
    POSITIVE LOGITS
    -than
    0.10
    wards
    0.09
    (after
    0.09
    -May
    0.09
    words
    0.09
    é¢ĩåħ·
    0.08
     blot
    0.08
    ila
    0.08
    Jam
    0.07
    /on
    0.07
    Activations Density 0.011%

    No Known Activations