© 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. 19120
    Prev
    Next
    INDEX
    Explanations

    see how, see why, see yourself

    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
    ä¸Ŀ毫
    -0.08
    è§IJ
    -0.08
    óng
    -0.08
    ibble
    -0.08
    directories
    -0.08
    åīįæıIJ
    -0.08
    akk
    -0.08
     Rag
    -0.08
     Bah
    -0.08
    oping
    -0.08
    POSITIVE LOGITS
    çĶŁäº§å·¥èīº
    0.10
    èĩªèº«çļĦ
    0.10
    éĿ¢ç²ī
    0.10
     Fet
    0.10
     Flickr
    0.09
     rằng
    0.09
    为åķ¥
    0.09
    íĭĢ
    0.09
    åİĨ
    0.09
    å¿ĥ缮ä¸Ń
    0.08
    Activations Density 0.029%

    No Known Activations