© 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. 55983
    Prev
    Next
    INDEX
    Explanations

    referring to a preceding noun

    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
    åľ¨æĪijçļĦ
    -0.09
    说åĪ°è¿ĻéĩĮ
    -0.08
    ên
    -0.08
    åĤ¨å¤ĩ
    -0.08
    CN
    -0.08
    ieve
    -0.08
     Mü
    -0.07
    åľ¨è¿Ļ个
    -0.07
    è·ŁæĪij说
    -0.07
     ÐłÐ¾ÑģÑģийÑģкой
    -0.07
    POSITIVE LOGITS
    èĢģ人家
    0.14
    åŀĴ
    0.12
    身影
    0.10
    为主线
    0.10
    /her
    0.10
    éĸĴ
    0.10
    èľĩ
    0.09
    raith
    0.09
    /th
    0.09
    å¸Ĥå§Ķ书记
    0.09
    Activations Density 0.272%

    No Known Activations