© 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. 30774
    Prev
    Next
    INDEX
    Explanations

    argued or decided dates

    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
    èĹľ
    -0.09
    æµ·æ°´
    -0.09
    åij¨åĽĽ
    -0.09
    åĿij
    -0.09
    æİ¢æµĭ
    -0.09
    걸
    -0.09
    à¹ģà¸Ļ
    -0.09
    è¿Ļç¯ĩ
    -0.08
    害
    -0.08
    lard
    -0.08
    POSITIVE LOGITS
    åħ¼èģĮ
    0.11
     arguments
    0.10
    arguments
    0.10
    dek
    0.09
    æ±ĩ
    0.09
    вÑĥ
    0.09
    lient
    0.09
    éħ·
    0.08
    /Input
    0.08
    æ²ī
    0.08
    Activations Density 0.131%

    No Known Activations