© 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. 38927
    Prev
    Next
    INDEX
    Explanations

    because of the

    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
    æľĢæľī
    -0.14
    æľĢåıĹ
    -0.12
    æľĢåħ·
    -0.12
    å¿ĥ仪çļĦ
    -0.11
    é¹Ħ
    -0.11
    æľĢåħ³éĶ®çļĦ
    -0.10
    æľĢåħĪè¿ĽçļĦ
    -0.10
    æľĢ主è¦ģçļĦ
    -0.10
     ÑģамÑĭе
    -0.10
     foremost
    -0.10
    POSITIVE LOGITS
    å¤§éĽ¨
    0.09
    ippers
    0.09
     vielen
    0.09
    лин
    0.09
    (using
    0.08
    WAR
    0.08
    ÙħÙĥاÙĨ
    0.08
    çĶ·æĸ¹
    0.08
    coe
    0.08
     необÑħодимоÑģÑĤи
    0.08
    Activations Density 0.227%

    No Known Activations