© 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. 50086
    Prev
    Next
    INDEX
    Explanations

    will be/become/serve

    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
    讲究
    -0.10
    å»Ĭ
    -0.10
    è¿Ļæīį
    -0.10
    åīįæīĢ
    -0.09
    å®ģæĦ¿
    -0.09
    æĹłæķ°
    -0.09
    æĸ¹æīį
    -0.09
     ÑĤомÑĥ
    -0.09
    æĪijä¸Ģ缴
    -0.09
     seemingly
    -0.09
    POSITIVE LOGITS
    ered
    0.16
    说æĺ¯
    0.12
    ering
    0.10
    /w
    0.10
    ines
    0.10
    ields
    0.10
    åģļçļĦäºĭ
    0.10
    mites
    0.09
    åģļçļĦ
    0.09
     бÑĭÑĤÑĮ
    0.09
    Activations Density 0.069%

    No Known Activations