© 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. 3362
    Prev
    Next
    INDEX
    Explanations

    autopsy and surgical procedures

    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
     trick
    -0.09
    éļıæīĭ
    -0.09
    åĵ®
    -0.09
    åĭ¾
    -0.08
    tical
    -0.08
    ponge
    -0.08
     Trick
    -0.08
    çľī
    -0.08
    AAD
    -0.08
     silently
    -0.08
    POSITIVE LOGITS
    åīĸ
    0.15
    åıĸåĩº
    0.11
    éű
    0.10
    éĿ³
    0.10
    bor
    0.10
    æĬ½åĩº
    0.10
    éĤ£æŶ
    0.09
    åīĸæŀIJ
    0.09
    å®ŀçī©
    0.09
    æł¸å¿ĥåĮº
    0.09
    Activations Density 0.373%

    No Known Activations