© 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. 22372
    Prev
    Next
    INDEX
    Explanations

    computer or device

    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
     Shutterstock
    -0.10
    æıª
    -0.09
    erer
    -0.09
    åļ¼
    -0.09
    éĿ©
    -0.09
     Cyr
    -0.08
    .live
    -0.08
    iliary
    -0.08
    inx
    -0.08
    åı¸é©¬
    -0.08
    POSITIVE LOGITS
    æ´¾åĩº
    0.10
    ä½łçļĦ
    0.10
    еÑī
    0.09
    .gb
    0.08
     cons
    0.08
     hers
    0.08
    建ç«ĭèµ·
    0.08
     strconv
    0.08
    ãģ®ãģĬ
    0.08
    家åºŃæķĻèĤ²
    0.08
    Activations Density 0.026%

    No Known Activations