© 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. 9436
    Prev
    Next
    INDEX
    Explanations

    units 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
    çĿĢ
    -0.09
    åĬ¨æijĩ
    -0.09
    é©´
    -0.09
    phoon
    -0.09
    ä¸įåłª
    -0.09
    çļĦä¸ĢåĪĩ
    -0.08
    nds
    -0.08
    _HANDLER
    -0.08
    马æĭī
    -0.08
    ä¸Ģè·¯
    -0.08
    POSITIVE LOGITS
     пÑĢог
    0.10
    anced
    0.09
    éĿ¢ç§¯çº¦
    0.08
    æľīåĩłä¸ª
    0.08
    俱
    0.08
    ild
    0.08
    ä½ľæĸĩ
    0.08
    ä¾ı
    0.08
    çŀĦ
    0.08
    ä¸ĵåĮº
    0.08
    Activations Density 0.032%

    No Known Activations