© 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. 17717
    Prev
    Next
    INDEX
    Explanations

    awarded for achievements

    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
    åIJİæĿ¥
    -0.08
    漫éķ¿çļĦ
    -0.08
    .bi
    -0.08
     extent
    -0.08
    çĻ½èī²çļĦ
    -0.08
    é¥
    -0.08
    кÑĢа
    -0.08
    ä¸Ģè¶Ł
    -0.08
    /star
    -0.08
    èĤ¥
    -0.08
    POSITIVE LOGITS
     being
    0.11
     having
    0.11
    æīĪ
    0.11
    being
    0.11
    幡
    0.10
    æĵħ
    0.09
    å²ļ
    0.09
    å±¥èģĮ
    0.09
    elden
    0.09
    çĪ±ä¸Ĭ
    0.09
    Activations Density 0.088%

    No Known Activations