© 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. 6361
    Prev
    Next
    INDEX
    Explanations

    Michelle Obama

    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
    ../../../
    -0.17
    çĦ¶æĺ¯
    -0.12
    åĦ¿
    -0.12
    ly
    -0.10
    edList
    -0.10
    ëģĶ
    -0.09
    eer
    -0.09
    er
    -0.09
    æĢ§å¼º
    -0.09
    å¾¼
    -0.09
    POSITIVE LOGITS
    èĩ¾
    0.11
    egration
    0.09
    ê¹IJ
    0.09
    æĸ°æĺ¥
    0.08
    ikk
    0.08
    ÙĨ
    0.08
    OrCreate
    0.08
    æĶ¯æĮģåĬĽåº¦
    0.08
    erna
    0.08
    ancy
    0.08
    Activations Density 0.045%

    No Known Activations