© 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. 53986
    Prev
    Next
    INDEX
    Explanations

    move to

    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
    èµŀ
    -0.09
     Guar
    -0.09
    è¡Įèµ°
    -0.09
    æĺ¯å¤ļå°ij
    -0.09
    èµŁ
    -0.09
    оп
    -0.08
    èįĢ
    -0.08
    UME
    -0.08
    alto
    -0.08
     Elk
    -0.08
    POSITIVE LOGITS
    迹象
    0.12
    åħ¬è®¤
    0.09
    ä¿ĥæĪIJ
    0.09
    GuidId
    0.08
    å°Ŀè¯ķ
    0.08
    decl
    0.08
    AVIS
    0.08
    mare
    0.08
    æĹ¶æľº
    0.08
    æļ®
    0.08
    Activations Density 0.018%

    No Known Activations