© 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. 38878
    Prev
    Next
    INDEX
    Explanations

    why, of, that, great, are, sort, do

    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
    urat
    -0.10
    rame
    -0.09
    áºŃp
    -0.09
    大å®ĹåķĨåĵģ
    -0.09
    ight
    -0.08
    汶
    -0.08
    è¿Ļ项
    -0.08
    æľīæľŁ
    -0.08
     Bust
    -0.08
    vara
    -0.08
    POSITIVE LOGITS
    å°ijè§ģ
    0.09
    åħ¸åŀĭçļĦ
    0.09
    è¿Ļç±»
    0.09
    å°±éľĢè¦ģ
    0.09
    æ»ĵ
    0.09
    å¹²äºĭ
    0.09
    agi
    0.09
    éĽį
    0.09
    å¯ĩ
    0.09
    ç³ľ
    0.09
    Activations Density 0.039%

    No Known Activations