© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37729
    Prev
    Next
    INDEX
    Explanations

    list items, roman numerals, or sections

    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
    ç»Ŀ大å¤ļæķ°
    -0.09
    人大
    -0.09
    asset
    -0.08
    大å¤ļæķ°äºº
    -0.08
    eri
    -0.08
    ç»Ŀ大éĥ¨åĪĨ
    -0.08
     nowhere
    -0.08
    æľįåĬ¡æ°´å¹³
    -0.08
    umps
    -0.08
    .createNew
    -0.08
    POSITIVE LOGITS
    å¦Ĥä½ķ
    0.12
    å¦Ĥä½ķçľĭå¾ħ
    0.10
    æĢİæł·
    0.10
    篾
    0.09
    ä»ĭç»į
    0.09
     how
    0.09
    æĪIJ为ä¸ĢåIJį
    0.09
    æĢİä¹Ī
    0.09
    讲æķħäºĭ
    0.09
     followed
    0.08
    Activations Density 0.062%

    No Known Activations