© 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. 27249
    Prev
    Next
    INDEX
    Explanations

    if you/we/I

    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
    åħµé©¬
    -0.09
    秣
    -0.08
    cken
    -0.08
    塵
    -0.08
    ç¹ģåįİ
    -0.08
    å¼ģ
    -0.08
    å¦Ħ
    -0.08
    æĿ¾å¼Ľ
    -0.08
     оÑĤдел
    -0.08
    .post
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.10
    å´ĸ
    0.10
    éĶĻäºĨ
    0.10
    ä¸įéĢĤ
    0.10
    è¾¾æłĩ
    0.09
    igers
    0.09
    -symbol
    0.09
    æį¢ä¸ª
    0.09
    ä¸Ģä¸Ŀ
    0.09
    è¿ĺæľī
    0.08
    Activations Density 0.010%

    No Known Activations