© 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. 49662
    Prev
    Next
    INDEX
    Explanations

    argument usage in text

    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
    èµ·æĿ¥äºĨ
    -0.10
    笼罩
    -0.09
    æ´ĭ
    -0.09
    å·¢
    -0.09
    éĵħ
    -0.09
    èĬ°
    -0.09
    ForKey
    -0.09
    еÑĢи
    -0.08
    人士
    -0.08
    èIJ
    -0.08
    POSITIVE LOGITS
     arguments
    0.18
    arguments
    0.16
    åıĤæķ°
    0.16
     argument
    0.14
     parameters
    0.14
    argument
    0.14
     Arguments
    0.14
     args
    0.13
     åıĤæķ°
    0.13
     parameter
    0.13
    Activations Density 0.626%

    No Known Activations