© 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. 6607
    Prev
    Next
    INDEX
    Explanations

    MacBook, Macbook, Firefox, PyQt

    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
    鲫
    -0.09
    edm
    -0.09
    atform
    -0.09
     пÑĢакÑĤи
    -0.08
    个åĪ«
    -0.08
    åģļæĪIJ
    -0.08
     пÑĢедÑĥÑģ
    -0.08
    itemId
    -0.08
    Ups
    -0.07
    å°ıåŃ©
    -0.07
    POSITIVE LOGITS
    .Callback
    0.09
    itter
    0.09
    ä¸įä½ı
    0.09
    éĻĩ
    0.09
    à¸Ńà¸ģ
    0.09
    اج
    0.09
    peare
    0.08
    纶
    0.08
    åĸľæ¬¢åIJĥ
    0.08
    èĦ²
    0.08
    Activations Density 0.012%

    No Known Activations