© 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. 57112
    Prev
    Next
    INDEX
    Explanations

    who is

    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
    éĤ£æ¬¡
    -0.09
    éĶĩ
    -0.09
    ä¸īæľŁ
    -0.09
    å¦ĤæľŁ
    -0.09
    æ³£
    -0.08
    å°ijä¸įäºĨ
    -0.08
    è¡¥
    -0.08
    exc
    -0.08
    éħĬ
    -0.08
    èĪ±
    -0.08
    POSITIVE LOGITS
    åľ¨ä¸Ģ个
    0.12
    被人
    0.09
    æĸĹ
    0.09
    ä¸į管
    0.09
     EIF
    0.09
    åĴĮä»ĸçļĦ
    0.09
    ÑĥÑģÑĤ
    0.08
     somehow
    0.08
    éĹ
    0.08
    åıªæľīä¸Ģ个
    0.08
    Activations Density 0.175%

    No Known Activations