© 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. 51015
    Prev
    Next
    INDEX
    Explanations

    dates back to ancient times

    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
    åĨįçĶŁ
    -0.09
    ä»İå°ıå°±
    -0.09
    Õ®
    -0.09
    ToDevice
    -0.09
    è¿Ļ两年
    -0.09
    FRING
    -0.09
    ä¿Ĺ
    -0.08
    URNS
    -0.08
    rego
    -0.08
    setDisplay
    -0.08
    POSITIVE LOGITS
    åı¤
    0.10
    æĬĬæĪij
    0.10
     ancient
    0.09
    æĺĶæĹ¥
    0.09
    åı¤ä»£
    0.09
    çª
    0.09
    åı¤äºº
    0.09
    åı¤èĢģ
    0.08
     Luo
    0.08
    å¹ħ
    0.08
    Activations Density 0.136%

    No Known Activations