© 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. 26702
    Prev
    Next
    INDEX
    Explanations

    right to

    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
    è¸Į
    -0.09
    اء
    -0.09
    ichel
    -0.09
     AsyncCallback
    -0.09
    è¾į
    -0.08
    读åIJİ
    -0.08
    为ä¹ĭ
    -0.08
    çIJĨäºĭä¼ļ
    -0.08
    æĴ¥
    -0.08
    以çĤº
    -0.08
    POSITIVE LOGITS
    æĿĥåĪ©
    0.13
    çļĦæĿĥåĪ©
    0.13
    çŁ¥æĥħ
    0.12
     rights
    0.12
     droit
    0.11
     пÑĢаво
    0.11
     derecho
    0.11
     Rights
    0.09
    æIJºå¸¦
    0.09
     quyá»ģn
    0.09
    Activations Density 0.054%

    No Known Activations