© 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. 5783
    Prev
    Next
    INDEX
    Explanations

    comparisons to other

    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
    ä¸Ģå®ļçļĦ
    -0.09
    è¯Ŀ
    -0.09
    iloc
    -0.09
    utz
    -0.09
    ä¹ĭåŁİ
    -0.09
     اÙĦÙħÙĨاسب
    -0.08
    åĶĨ
    -0.08
    åħ¨äº§ä¸ļéĵ¾
    -0.08
    çķ¶åľ°
    -0.08
    alem
    -0.08
    POSITIVE LOGITS
    åIJĮç±»
    0.16
    主æµģ
    0.11
    åIJĮçŃī
    0.10
    åħ¶ä»ĸ
    0.10
     comparable
    0.09
    åħ¶ä»ĸçļĦ
    0.09
     elsewhere
    0.09
    ä»ĸãģ®
    0.09
    åħ¶å®ĥ
    0.09
    缸è¿ij
    0.09
    Activations Density 0.095%

    No Known Activations