© 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. 4547
    Prev
    Next
    INDEX
    Explanations

    the scientific

    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
     Trace
    -0.09
    åŁİå¸Ĥ管çIJĨ
    -0.09
    едÑĮ
    -0.09
    æľĢ大çļĦ
    -0.09
    å¥ī
    -0.09
    bow
    -0.08
    å¾Ĺ天
    -0.08
    .asc
    -0.08
    оз
    -0.08
    éĽį
    -0.08
    POSITIVE LOGITS
    è´¨éĩıåĴĮ
    0.10
    æİīèIJ½
    0.09
     content
    0.09
     quantity
    0.09
    æĻĵ
    0.09
    еÑĢе
    0.09
    å¢Ł
    0.09
    åħ®
    0.09
    åīįéĢĶ
    0.08
     information
    0.08
    Activations Density 0.030%

    No Known Activations