© 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. 48153
    Prev
    Next
    INDEX
    Explanations

    recent or previous followed by an event/publication

    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
    缸åıį
    -0.09
     же
    -0.09
    åºĶæľīçļĦ
    -0.09
    èĶº
    -0.08
     Rest
    -0.08
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.08
    _rest
    -0.08
    åłĩ
    -0.08
    åij¨æľ«
    -0.08
    åıįä¹ĭ
    -0.08
    POSITIVE LOGITS
     Celt
    0.09
     Conse
    0.09
    æŁIJ
    0.08
    lsi
    0.08
    ockets
    0.08
    飶
    0.08
    æµ·è¿IJ
    0.08
     пÑĢид
    0.08
    åIJĮæľŁ
    0.08
    vez
    0.08
    Activations Density 0.058%

    No Known Activations