© 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. 22447
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    é¦ģ
    -0.09
    åĪĨ解
    -0.09
    çľģåĨħ
    -0.08
    -lang
    -0.08
    ÃŃg
    -0.08
     âĸij
    -0.08
    CSR
    -0.08
    ãĥįãĤ¿
    -0.08
     wee
    -0.08
    å¦Ĥä¸ĭ
    -0.08
    POSITIVE LOGITS
    èĩ³æѤ
    0.08
    æľīè¿Ļæł·çļĦ
    0.08
    æ±Łå±±
    0.08
    elib
    0.08
    æѤç§į
    0.08
    agma
    0.08
    èĢģ人家
    0.08
    è¿ĻæĶ¯
    0.08
    æ¸ħæĸ°
    0.08
    åĩºèº«
    0.08
    Activations Density 0.678%

    No Known Activations