© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11298
    Prev
    Next
    INDEX
    Explanations

    ProcessExplorer, EventGhost, TortoiseSVN

    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
    pon
    -0.10
    .Css
    -0.09
    æ¿®
    -0.09
    æ·ĺ
    -0.08
     Ying
    -0.08
    æĦı大
    -0.08
    ä¸ºæľŁ
    -0.08
    GY
    -0.08
    汩
    -0.08
    èµĦ
    -0.08
    POSITIVE LOGITS
    æłĮ
    0.10
    æīĩ
    0.09
    tte
    0.09
    èļĮ
    0.09
    æ¦ľ
    0.09
    argar
    0.09
    çľĭå®Į
    0.09
    stead
    0.08
    åľ¨è¿Ļ个
    0.08
    Å¡t
    0.08
    Activations Density 0.053%

    No Known Activations