© 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. 58038
    Prev
    Next
    INDEX
    Explanations

    process called

    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
    次è¦ģ
    -0.09
    ören
    -0.08
    å¤ļ个
    -0.08
    çŃīå¤ļç§į
    -0.08
    妨
    -0.08
    åĪİ
    -0.08
    æįį
    -0.08
    ãģĦãģ¤
    -0.07
    äºĮ级
    -0.07
    å¤ļç§į
    -0.07
    POSITIVE LOGITS
    åı«åģļ
    0.33
    åIJį为
    0.26
    称为
    0.25
    åIJįåı«
    0.24
    被称为
    0.24
    称ä¹ĭ为
    0.23
     called
    0.22
    called
    0.21
    åı«
    0.20
     наз
    0.17
    Activations Density 0.222%

    No Known Activations