© 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. 18922
    Prev
    Next
    INDEX
    Explanations

    approximations followed by numbers

    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
    ago
    -0.10
    å¡ŀ
    -0.09
    éĢ¾
    -0.09
    å°±è¿ŀ
    -0.08
    ä¹Łä¸įçŁ¥éģĵ
    -0.08
    åĨįä¹Łæ²¡æľī
    -0.08
    acious
    -0.08
    ws
    -0.08
    æ®Ĩ
    -0.08
    ages
    -0.08
    POSITIVE LOGITS
     sco
    0.09
    çIJ¦
    0.09
    第ä¸Ģå±Ĭ
    0.09
    .GetData
    0.09
    ä»Ĭ天çļĦ
    0.09
    代表大ä¼ļ
    0.09
    å¿«æĬ¥
    0.09
    æīĭåĨĮ
    0.09
    _REGS
    0.09
    åįļ
    0.09
    Activations Density 0.068%

    No Known Activations