© 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. 31145
    Prev
    Next
    INDEX
    Explanations

    Lagos State University

    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
    ç«Ń
    -0.11
    alon
    -0.10
    killer
    -0.09
    夷
    -0.09
    uffs
    -0.09
    ç¾İçļĦ
    -0.09
    æĬĺ
    -0.08
    atten
    -0.08
     اÙĦطبÙĬعÙĬ
    -0.08
    eus
    -0.08
    POSITIVE LOGITS
    éŀĭåŃIJ
    0.09
    èį«
    0.09
    èĩªæ²»åĮº
    0.09
    \Has
    0.09
    å¡Į
    0.09
    ÙĪبا
    0.08
    æĹĹèĪ°åºĹ
    0.08
    éºĵ
    0.08
    åIJij社ä¼ļ
    0.08
    าย
    0.08
    Activations Density 0.024%

    No Known Activations