© 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. 56803
    Prev
    Next
    INDEX
    Explanations

    the first / was the

    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
    æ¯ı次éĥ½
    -0.10
    è¿Ļ件äºĭæĥħ
    -0.10
    eft
    -0.10
    оÑĩно
    -0.09
    è¿Ħä»Ĭ
    -0.09
    جÙĬÙĨ
    -0.09
    è¿Ļäºĭ
    -0.09
    åĸ»
    -0.09
    çݩ游æĪı
    -0.08
    rens
    -0.08
    POSITIVE LOGITS
    åĻ¨å®ĺ
    0.09
     unpl
    0.09
     salv
    0.08
    è·¸
    0.08
    çī¹ç§į
    0.08
    ç²¾åįİ
    0.08
    æĦŁäºº
    0.08
    åħ¨éĿ¢èIJ½å®ŀ
    0.08
    伪
    0.08
    wie
    0.08
    Activations Density 0.024%

    No Known Activations