© 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. 37590
    Prev
    Next
    INDEX
    Explanations

    start uml, long last

    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
    亢
    -0.09
    ermen
    -0.08
    å«Įçĸij
    -0.08
    ermal
    -0.08
     Lent
    -0.08
    æĪ´
    -0.08
    æľĢé«ĺçļĦ
    -0.08
     Gast
    -0.08
    phas
    -0.08
    æŁ³
    -0.08
    POSITIVE LOGITS
    éķ¿åŁİ
    0.10
    æ´Ĵ
    0.10
    æĴĴ
    0.09
     Meh
    0.09
    ossa
    0.09
    ç¦ģ
    0.09
    趺
    0.09
    åħ®
    0.08
    éĢij
    0.08
    hei
    0.08
    Activations Density 0.100%

    No Known Activations