© 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. 56728
    Prev
    Next
    INDEX
    Explanations

    -shaped, disulfide-linked, hairpin-loop

    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
    Çļ
    -0.10
    jerne
    -0.10
    iage
    -0.09
    æµĶ
    -0.09
    æ²¹èĦĤ
    -0.09
    称为
    -0.09
     pil
    -0.09
    losure
    -0.08
    æľĭåıĭ们
    -0.08
    é¢Ĩä¼ļ
    -0.08
    POSITIVE LOGITS
    -shaped
    0.11
    éĤ£æ¬¡
    0.11
    éĵĽ
    0.08
    ToLocal
    0.08
    æł·çļĦ
    0.08
    æľīå¿ħè¦ģ
    0.08
    STONE
    0.08
    ooting
    0.08
     bầu
    0.08
     jub
    0.08
    Activations Density 0.012%

    No Known Activations