© 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. 57211
    Prev
    Next
    INDEX
    Explanations

    every [noun]

    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
    berger
    -0.11
    ç¬ĭ
    -0.11
    æľ¬ç½ij
    -0.10
    æĻļæĬ¥
    -0.09
    æŁIJäºĽ
    -0.09
    é¦ĸä½į
    -0.08
     пеÑĢвÑĥÑİ
    -0.08
    ä¸ĬçıŃ
    -0.08
    stance
    -0.08
    gis
    -0.08
    POSITIVE LOGITS
    iating
    0.10
    ä¸Ģä¸Ŀ
    0.10
    大大å°ıå°ı
    0.09
    æ²½
    0.09
    /lg
    0.09
    åŀ¸
    0.09
    æĸ¹éĿ¢çļĦ
    0.09
    oting
    0.09
    иÑı
    0.09
    illes
    0.09
    Activations Density 0.032%

    No Known Activations