© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50822
    Prev
    Next
    INDEX
    Explanations

    pop up

    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
    erras
    -0.10
    å¬ĸ
    -0.10
    éĢĶ
    -0.10
    вой
    -0.09
    ç»ķ
    -0.09
    贯彻
    -0.09
    áĥ¬
    -0.09
     пÑĥÑĤ
    -0.09
    ror
    -0.08
    oping
    -0.08
    POSITIVE LOGITS
    åľ¨åIJĮä¸Ģ
    0.10
    /pop
    0.09
    åĤ
    0.09
    æıIJä¾ĽæĽ´å¤ļ
    0.09
    çĥ¯
    0.09
     champagne
    0.09
    è·³åĩº
    0.09
    å¼ĢæĿ¥
    0.09
    å²ĺ
    0.09
     popped
    0.08
    Activations Density 0.158%

    No Known Activations