© 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. 35444
    Prev
    Next
    INDEX
    Explanations

    favorite

    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
    ĥģ
    -0.11
    AGMA
    -0.09
    æ´»ä¸ĭåİ»
    -0.09
     możliwoÅĽci
    -0.08
    ç³»
    -0.08
    åĿĿ
    -0.08
    .reply
    -0.08
    esar
    -0.08
    åħ¨æĸ¹ä½į
    -0.08
    åĭŁéĽĨ
    -0.08
    POSITIVE LOGITS
     favorite
    0.20
    æľĢåĸľæ¬¢çļĦ
    0.18
    æľĢçĪ±
    0.18
     favourite
    0.18
    favorite
    0.17
     лÑİбим
    0.17
    æľĢåĸľæ¬¢
    0.17
    åĸľçĪ±
    0.16
    Favorite
    0.15
    .favorite
    0.14
    Activations Density 0.061%

    No Known Activations