© 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. 53750
    Prev
    Next
    INDEX
    Explanations

    how is/are X?

    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
    chè
    -0.08
     SD
    -0.08
    SD
    -0.08
    ç§ī
    -0.08
    onian
    -0.08
    oppers
    -0.08
     zwar
    -0.08
    æĺ¨æĹ¥
    -0.08
    дей
    -0.08
     saw
    -0.08
    POSITIVE LOGITS
    æ²¥
    0.10
    ãģªãģĬ
    0.10
    ä¸ĢæĿ¯
    0.09
    æ¡£æ¡Ī
    0.09
    æľĢåħ³éĶ®çļĦ
    0.09
    çģ«çĥ§
    0.09
    è¿ĩæĿ¥
    0.09
    ä¸Ģé¢Ĺ
    0.08
    iana
    0.08
    ä¸Ģæľ¬ä¹¦
    0.08
    Activations Density 0.026%

    No Known Activations