© 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. 38160
    Prev
    Next
    INDEX
    Explanations

    individuals and entities

    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
    åĸ·
    -0.08
    æĮĩæķ°
    -0.08
    好åIJĥ
    -0.08
    pyx
    -0.08
    raw
    -0.08
     prov
    -0.08
    eldon
    -0.08
    åĪĿ
    -0.08
    è¿Ļ个è¡Įä¸ļ
    -0.08
    arra
    -0.07
    POSITIVE LOGITS
    æ³ķ人
    0.22
    åĴĮ个人
    0.17
    å®ŀä½ĵ
    0.12
    æ³ķå®ļ代表
    0.12
     ê°ľìĿ¸
    0.12
    entity
    0.11
    éĥ¦
    0.11
     лиÑĨа
    0.11
     corporate
    0.11
    个人
    0.11
    Activations Density 0.066%

    No Known Activations