© 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. 5274
    Prev
    Next
    INDEX
    Explanations

    delay or backlog

    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
    å®ļæŶ
    -0.10
    å¦Ĥæľīä¾µæĿĥ
    -0.09
     collaps
    -0.09
     Bab
    -0.08
    æĻŁ
    -0.08
     ÑģпеÑĨ
    -0.08
     Dim
    -0.08
    循çݯ
    -0.08
     cầm
    -0.08
    ota
    -0.08
    POSITIVE LOGITS
    æİĴéĺŁ
    0.15
    çŃīåĢĻ
    0.12
    çŃīå¾ħ
    0.11
    å»¶è¿Ł
    0.11
    è¾ĥéķ¿
    0.11
     backlog
    0.11
     оÑĩеÑĢед
    0.11
    Delay
    0.11
     оÑĩеÑĢедÑĮ
    0.11
     delays
    0.11
    Activations Density 0.090%

    No Known Activations