© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9878
    Prev
    Next
    INDEX
    Explanations

    version of

    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
    ä»»åij½
    -0.09
    ил
    -0.09
    åIJĪçIJĨçļĦ
    -0.09
    elic
    -0.09
    æŃ»è§Ĵ
    -0.09
    åIJĪéĢĤçļĦ
    -0.08
    认è¯Ĩ
    -0.08
    åŃľ
    -0.08
    elin
    -0.08
    .cgi
    -0.08
    POSITIVE LOGITS
    æı¡
    0.09
    ä»Ģä¹Īåı«
    0.09
    å¿Į
    0.09
    说è¿ĩ
    0.09
    æķ°æį®æĺ¾ç¤º
    0.09
    ãĤ¢ãĤ¦
    0.08
    踮
    0.08
    ä¾£
    0.08
    æı¡ä½ı
    0.08
    mage
    0.08
    Activations Density 0.102%

    No Known Activations