© 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. 31455
    Prev
    Next
    INDEX
    Explanations

    european cave paintings

    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
    åķ®
    -0.10
    ä»ĭ
    -0.10
    å¼ĢçĿĢ
    -0.10
    åķĦ
    -0.09
    笼
    -0.09
     ANSI
    -0.09
    ç³Ĺ
    -0.09
    mate
    -0.09
    æļĮ
    -0.09
    éĮ¾
    -0.08
    POSITIVE LOGITS
    preh
    0.10
    ILT
    0.09
    _imgs
    0.09
    éĥ¨èIJ½
    0.09
    sole
    0.09
     Sole
    0.09
    æĭ©
    0.09
    ç¥Ńç¥Ģ
    0.09
    ozo
    0.09
     hunter
    0.08
    Activations Density 0.063%

    No Known Activations