© 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. 35368
    Prev
    Next
    INDEX
    Explanations

    Magdalene, Madeleine, Evangeline, Maddaloni

    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
    èĢ¿
    -0.10
    lessly
    -0.09
    让人们
    -0.09
    åIJ±
    -0.09
    itchens
    -0.09
    羣æĥħ
    -0.09
    aid
    -0.09
    åĮł
    -0.08
    让èĩªå·±
    -0.08
    plementation
    -0.08
    POSITIVE LOGITS
    leine
    0.10
    æľĪä¸ĭ
    0.09
    ëģĶ
    0.09
    thed
    0.08
    emat
    0.08
     اÙĦدÙĨÙĬا
    0.08
    uled
    0.08
    istrator
    0.08
    oris
    0.08
     Horny
    0.08
    Activations Density 0.007%

    No Known Activations