© 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. 33775
    Prev
    Next
    INDEX
    Explanations

    special characters or specific words

    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
     razor
    -0.08
     Cous
    -0.08
    海绵
    -0.07
    Ñģлав
    -0.07
    .gs
    -0.07
     Flor
    -0.07
    portal
    -0.07
    æĴĩ
    -0.07
     rarely
    -0.07
    pr
    -0.07
    POSITIVE LOGITS
    æīĢåľ¨çļĦ
    0.12
    ä¹Łä¸įæĥ³
    0.12
    è§ĤçĤ¹
    0.10
    æīĢåľ¨
    0.10
    yll
    0.10
    æľ¬äºº
    0.10
    ANGLES
    0.10
    åºŀ大çļĦ
    0.10
    æĸĩåĮĸåĴĮ
    0.10
    ìĺ³
    0.10
    Activations Density 0.026%

    No Known Activations