© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51910
    Prev
    Next
    INDEX
    Explanations

    quintiles, percentiles, quartiles

    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
    鼶è·Ŀ离
    -0.10
    çıı
    -0.09
    Ñĥж
    -0.09
    enn
    -0.09
    åĬ©
    -0.09
    lash
    -0.08
    cka
    -0.08
    çħ¨
    -0.08
    ngle
    -0.08
    гоÑĤов
    -0.08
    POSITIVE LOGITS
    è¡ĮåĬ¨è®¡åĪĴ
    0.09
    大ä¼Ĺ
    0.08
    éĥİ
    0.08
    æĭĴç»Ŀ
    0.08
     báºŃc
    0.08
    Parms
    0.08
     Spells
    0.08
    åIJĮç±»
    0.08
    оз
    0.08
    ç¯ĵ
    0.08
    Activations Density 0.043%

    No Known Activations