© 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. 57215
    Prev
    Next
    INDEX
    Explanations

    Go, modular, written, intended

    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
    clave
    -0.08
    å¥İ
    -0.08
    ivic
    -0.08
    æĬĬæݧ
    -0.08
    交ä¼ļ
    -0.08
     Clem
    -0.08
     rub
    -0.08
    æ°ijçĶŁ
    -0.08
    ervo
    -0.07
    æľīæķĪæĢ§
    -0.07
    POSITIVE LOGITS
    èĥ½æ»¡è¶³
    0.09
    оÑģÑĤей
    0.09
     вÑĭÑĢажен
    0.09
    æĿĵ
    0.09
    å¢ŀè¿Ľ
    0.09
     yat
    0.09
    æij©æīĺ车
    0.09
    stral
    0.08
    볨
    0.08
    казал
    0.08
    Activations Density 0.413%

    No Known Activations