© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16658
    Prev
    Next
    INDEX
    Explanations

    political campaigns, news, issues, thought

    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
    Negative Logits
    èĩ¾
    -0.09
    峨
    -0.09
    ror
    -0.09
    è´°
    -0.09
    inite
    -0.09
    ingly
    -0.09
    æĮģèĤ¡
    -0.09
    æ±Ŀ
    -0.09
    ry
    -0.09
    ugg
    -0.09
    POSITIVE LOGITS
    -economic
    0.10
    aina
    0.10
    -party
    0.10
    lectic
    0.09
    å·¥ä½ľèĢħ
    0.09
    -cultural
    0.09
    /social
    0.08
    æīĭèħķ
    0.08
    åĭĻ
    0.08
    ynomials
    0.08
    Activations Density 0.021%

    No Known Activations