© 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. 38883
    Prev
    Next
    INDEX
    Explanations

    all matters and times

    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
    æµĨ
    -0.09
    Hang
    -0.09
    åIJİæŀľ
    -0.08
    sey
    -0.08
     Hang
    -0.08
    鸳
    -0.08
    agger
    -0.08
     hung
    -0.07
     TE
    -0.07
    successful
    -0.07
    POSITIVE LOGITS
    ä½ŀ
    0.12
    åħľ
    0.09
    RV
    0.09
    å²ļ
    0.09
    çĻĤ
    0.09
    èIJ½åľ¨
    0.09
    åºľ
    0.08
    çĥĬ
    0.08
    ä¸įåŃķ
    0.08
    obel
    0.08
    Activations Density 0.211%

    No Known Activations