© 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. 39887
    Prev
    Next
    INDEX
    Explanations

    from the

    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
     пÑĢид
    -0.09
    çħ¦
    -0.08
    æ°Ķ
    -0.08
    å°ı康
    -0.08
    DataTable
    -0.08
    代è¨Ģ
    -0.08
    ä¸Ģ份
    -0.08
    èģĮ
    -0.08
    esto
    -0.08
    emark
    -0.08
    POSITIVE LOGITS
    æĮĩå°ĸ
    0.09
    öt
    0.08
    åİŁæĿ¥
    0.08
    nock
    0.08
     أجÙĦ
    0.08
    çķ¥å¾®
    0.08
    å®ĺæĸ¹
    0.08
    ç¥ŀ
    0.08
    åģļèµ·
    0.08
    æķ°åįĥ
    0.08
    Activations Density 0.158%

    No Known Activations