© 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. 19010
    Prev
    Next
    INDEX
    Explanations

    virtualization and emulation

    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
    åĮ»æĬ¤
    -0.10
    åºĶæĶ¶
    -0.09
    akedown
    -0.09
    Content
    -0.09
    æįĤ
    -0.09
     Content
    -0.08
    eselect
    -0.08
    ëį°ìĿ´
    -0.08
    MainThread
    -0.08
    stairs
    -0.08
    POSITIVE LOGITS
    èĻļæĭŁ
    0.11
     virtual
    0.10
    模æĭŁ
    0.10
    éļĶ离
    0.10
    çݯå¢ĥ
    0.09
    çݯå¢ĥä¸ĭ
    0.09
    å®ŀéªĮ室
    0.09
    ä»¿çľŁ
    0.09
     emulator
    0.09
     ÑĥÑĩеб
    0.09
    Activations Density 0.351%

    No Known Activations