© 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. 61317
    Prev
    Next
    INDEX
    Explanations

    software development

    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
     sog
    -0.10
    ä¸įæĿ¥
    -0.09
    èĪįå¾Ĺ
    -0.09
    èĬĤ缮
    -0.08
    åĨł
    -0.08
    åľ¨çº¿
    -0.08
    oppable
    -0.08
    izzy
    -0.08
     crem
    -0.08
    aal
    -0.08
    POSITIVE LOGITS
    çıŃç»Ħ
    0.10
    ä¸ĵä¸ļåĮĸ
    0.10
     fark
    0.10
    ãĤ«ãĥ³
    0.10
    éĩįå·¥
    0.09
    ä¸ĩè¾¾
    0.09
    Sq
    0.08
    æķ´æ´ģ
    0.08
    erno
    0.08
     transition
    0.08
    Activations Density 0.113%

    No Known Activations