© 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. 51733
    Prev
    Next
    INDEX
    Explanations

    types of

    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¸Ģå¹ħ
    -0.10
    ä¸Ģç³»åĪĹ
    -0.09
    oom
    -0.09
    ä¸Ģæĸ¹
    -0.09
    CADE
    -0.08
    ìħĢ
    -0.08
    æīĢæıIJä¾ĽçļĦ
    -0.08
    æľīä¸Ģ天
    -0.08
    ä¸ĢéĿ¢
    -0.08
    æĸĻ
    -0.08
    POSITIVE LOGITS
    stalk
    0.10
    å¯Ł
    0.10
    AZE
    0.09
    accom
    0.09
    è´¤
    0.09
    Sab
    0.08
    èĥª
    0.08
    è¿ijè·Ŀ离
    0.08
     accom
    0.08
    obl
    0.08
    Activations Density 0.084%

    No Known Activations