© 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. 48038
    Prev
    Next
    INDEX
    Explanations

    is followed by definition or description

    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
    讳
    -0.09
    æī¯
    -0.09
    çīĪæĿĥ声æĺİ
    -0.09
     jon
    -0.08
    ather
    -0.08
    éº»æľ¨
    -0.08
    浪
    -0.08
    æ¯ĶæĪij
    -0.08
    æ¡¢
    -0.08
     пока
    -0.08
    POSITIVE LOGITS
    èĩ´åĬĽäºİ
    0.11
    çİ°å·²
    0.10
    æĺ¯æĪij
    0.10
    ä¸ĸçķĮä¸ĬæľĢ
    0.10
    åħ¨æĸ°çļĦ
    0.09
    è¿Ī
    0.09
    URED
    0.09
    对åħ¶è¿Ľè¡Į
    0.08
    ä¿Ŀè¯ģ
    0.08
     Sour
    0.08
    Activations Density 0.058%

    No Known Activations