© 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. 32158
    Prev
    Next
    INDEX
    Explanations

    jr. and names ending in -o or -ar

    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
    romo
    -0.09
    >Show
    -0.09
    æĥ³ä¸įåĪ°
    -0.09
    uger
    -0.09
    enser
    -0.09
    éĺĴ
    -0.09
    è¿Ļç¬Ķ
    -0.08
    å·¥ä½ľä»»åĬ¡
    -0.08
    éļħ
    -0.08
    çļĩ家
    -0.08
    POSITIVE LOGITS
    è¿ijè·Ŀ离
    0.09
    ç¥Ģ
    0.09
    ä¸Ģåı£
    0.08
     Nar
    0.08
    iar
    0.08
    çļĦ身影
    0.08
    æ»ĭ
    0.08
    arts
    0.08
    形象
    0.08
    æĮ¨
    0.08
    Activations Density 0.001%

    No Known Activations