© 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. 30961
    Prev
    Next
    INDEX
    Explanations

    templates for specific forms

    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
    æĹ¢èĥ½
    -0.10
    满æĢĢ
    -0.09
    portun
    -0.08
     обÑĢаÑĤ
    -0.08
    è²Ĥ
    -0.08
     Opport
    -0.08
     Eaton
    -0.08
    é»Ħæĺı
    -0.08
     Paran
    -0.08
    ersion
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·çļĦ
    0.09
    lit
    0.09
    Lit
    0.08
    ä¸İåIJ¦
    0.08
    è¿Ļæł·çļĦè¯Ŀ
    0.08
     lit
    0.08
    æľ¬äºº
    0.08
    Cold
    0.08
    arkin
    0.08
    äºŃ
    0.08
    Activations Density 1.168%

    No Known Activations