© 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. 33267
    Prev
    Next
    INDEX
    Explanations

    counting and distinguishing items

    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
    å°ijè§ģ
    -0.09
    веден
    -0.08
     ê°ģì¢ħ
    -0.08
    _REGS
    -0.08
    大éĩı
    -0.08
    åİĨ代
    -0.08
    æķ´ä¸ªäºº
    -0.08
    è¿Ļåı¥è¯Ŀ
    -0.08
    7
    -0.08
    9
    -0.08
    POSITIVE LOGITS
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.22
    åħ¶ä¸Ńä¸Ģ个
    0.22
    ä¸Ģ个æĺ¯
    0.16
     ones
    0.15
    æľīçļĦ
    0.14
    第ä¸Ģ个
    0.13
    ä¹ĭä¸Ģ
    0.13
    åĵªä¸Ģ个
    0.13
    åħ¶ä¸Ńæľī
    0.13
     ÙħÙĨÙĩÙħ
    0.13
    Activations Density 0.500%

    No Known Activations