© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52771
    Prev
    Next
    INDEX
    Explanations

    fees and dues

    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
    longleftrightarrow
    -0.09
    ä¸ĢçĤ¹éĥ½ä¸į
    -0.08
     __________________↵↵
    -0.08
     xếp
    -0.08
    åīį线
    -0.08
    åħ´å¥ĭ
    -0.08
    æİĴåIJį第
    -0.08
    볤
    -0.08
    ations
    -0.08
    篱
    -0.08
    POSITIVE LOGITS
    ño
    0.10
    ç°ª
    0.10
     Larson
    0.10
    unders
    0.09
     tây
    0.09
    ForResult
    0.09
    ìĦľ
    0.09
    è¿ŀè½½
    0.08
    пÑĢе
    0.08
    å©
    0.08
    Activations Density 0.002%

    No Known Activations