© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52197
    Prev
    Next
    INDEX
    Explanations

    fact that / without that

    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
    antha
    -0.10
    çķ¿
    -0.09
    -Ta
    -0.09
    enas
    -0.09
    è¦ģåѦä¼ļ
    -0.09
    èĻļåģĩ
    -0.09
    好æĦŁ
    -0.09
    íĮIJ
    -0.09
     Void
    -0.08
    @Spring
    -0.08
    POSITIVE LOGITS
    onian
    0.10
    åı¦ä¸Ģä½į
    0.09
    éĤ£ä¹Īç®Ģåįķ
    0.09
    tes
    0.08
    Ùħرا
    0.08
    pped
    0.08
    ocket
    0.08
    æİ¨è¿Ł
    0.08
     existence
    0.07
    kus
    0.07
    Activations Density 0.004%

    No Known Activations