© 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. 2883
    Prev
    Next
    INDEX
    Explanations

    put in place mechanisms

    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
    å¼Ģåħ·
    -0.10
    æľIJ
    -0.09
    æĸ°å¼Ģ
    -0.08
    åIJĮæľŁ
    -0.08
    èĦ¸
    -0.08
    毫
    -0.08
    é¢Ħè§ģ
    -0.08
    IID
    -0.08
    uka
    -0.08
    使çĶ¨æĿĥ
    -0.08
    POSITIVE LOGITS
    æݪæĸ½
    0.15
     mechanisms
    0.14
    æľºåĪ¶
    0.13
     measures
    0.12
     меÑħанизм
    0.12
     processes
    0.12
    Processes
    0.11
     Measures
    0.11
    åĪ°ä½į
    0.10
    à¹Ħว
    0.10
    Activations Density 0.052%

    No Known Activations