© 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. 54281
    Prev
    Next
    INDEX
    Explanations

    cytochrome P450

    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
     Suarez
    -0.09
    ngr
    -0.09
    åĸĩåıŃ
    -0.09
    SKI
    -0.08
    ycin
    -0.08
    .ef
    -0.08
     Ella
    -0.08
    yleft
    -0.08
    ÙĬÙĦا
    -0.08
    iped
    -0.08
    POSITIVE LOGITS
    isman
    0.09
    ä¸Ģ举
    0.09
    ä¸Ģåı£æ°Ķ
    0.09
    rael
    0.09
    é¾ĭ
    0.09
    éĥ¨ä¸»ä»»
    0.09
    åħ´ä¸ļ
    0.08
    éĥ¨éĥ¨éķ¿
    0.08
    ê¼Ń
    0.08
    aways
    0.08
    Activations Density 0.260%

    No Known Activations