© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40261
    Prev
    Next
    INDEX
    Explanations

    fro followed by specific suffixes

    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
    Negative Logits
    uate
    -0.10
    åĴª
    -0.09
    пл
    -0.09
    onde
    -0.08
    ä¸ļä½Ļ
    -0.08
    ëģĶ
    -0.08
     contrario
    -0.08
    dcc
    -0.08
     pylint
    -0.08
    ael
    -0.08
    POSITIVE LOGITS
    媳
    0.10
    é¹ķ
    0.10
    eward
    0.10
    è¡·
    0.10
    bery
    0.09
    缼ä¼ļ
    0.09
    vided
    0.09
    cents
    0.09
    åĥı个
    0.09
    zier
    0.09
    Activations Density 0.012%

    No Known Activations