© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38053
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
    æĩĭ
    -0.10
    ãĤ¹ãĤ¿ãĥ¼
    -0.09
    -most
    -0.09
    ÑģоÑģ
    -0.09
     cris
    -0.09
    ê°¯
    -0.09
    å±į
    -0.09
     Knife
    -0.09
    listed
    -0.09
    éĩĮæĸ¯
    -0.08
    POSITIVE LOGITS
     redistrib
    0.09
    entifier
    0.08
     tender
    0.08
    wie
    0.08
    é»ijé¾Ļ
    0.08
    sole
    0.07
     DateTimeKind
    0.07
    0
    0.07
    ifice
    0.07
    åįİåįĹ
    0.07
    Activations Density 0.378%

    No Known Activations