© 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. 5896
    Prev
    Next
    INDEX
    Explanations

    additional grant, full listing

    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
     same
    -0.11
    们
    -0.11
     actual
    -0.10
    ses
    -0.10
     footage
    -0.09
     stuff
    -0.09
    ves
    -0.09
    çļĦä¸Ģç§į
    -0.08
     grounds
    -0.08
    lep
    -0.08
    POSITIVE LOGITS
    说ä¸įåĩº
    0.10
    çģµéŃĤ
    0.10
    kees
    0.10
    æѤ
    0.10
    å¾Īéĩįè¦ģçļĦ
    0.10
    ãĥ©ãĤ¤
    0.09
    该游æĪı
    0.09
    .references
    0.09
    .timestamps
    0.09
    ä¸įå°ıçļĦ
    0.09
    Activations Density 2.290%

    No Known Activations