© 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. 30896
    Prev
    Next
    INDEX
    Explanations

    filter, permission, commercial use

    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
    unread
    -0.09
    ctors
    -0.08
    åĨħå¤ĸ
    -0.08
    ritz
    -0.08
    éĢıè§Ĩ
    -0.08
    (alias
    -0.08
    è¡ĮæĿİ
    -0.08
    -push
    -0.08
    Safety
    -0.08
    å±Ģéķ¿
    -0.07
    POSITIVE LOGITS
    ä½ľåĵģ
    0.12
     commercial
    0.11
    åķĨæ¥Ń
    0.11
    åķĨä¸ļåĮĸ
    0.11
    åķĨä¸ļ
    0.11
    çļĦä½ľåĵģ
    0.10
    Commercial
    0.10
    commercial
    0.10
    åĪĽä½ľ
    0.10
    欣èµı
    0.09
    Activations Density 0.070%

    No Known Activations