© 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. 57469
    Prev
    Next
    INDEX
    Explanations

    Israel

    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
    emp
    -0.09
    èī²è°ĥ
    -0.09
    ryn
    -0.09
    лив
    -0.09
    ëį°
    -0.08
    åıįæĢĿ
    -0.08
    ging
    -0.08
    iso
    -0.08
    ä¸ŃåĽ½å¸Ĥåľº
    -0.08
    æĢµ
    -0.08
    POSITIVE LOGITS
    ãĤĪãģĨãģª
    0.10
    owitz
    0.10
    wich
    0.09
    anne
    0.09
    é£İä¿Ĺ
    0.09
    èIJĮ
    0.09
    duino
    0.09
    baum
    0.09
    ivity
    0.09
    ine
    0.08
    Activations Density 0.012%

    No Known Activations