© 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. 27479
    Prev
    Next
    INDEX
    Explanations

    protocol

    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
    æĥħåĨµè¿Ľè¡Į
    -0.09
    æįį
    -0.08
    SOFTWARE
    -0.08
    antas
    -0.08
    å¤©çľŁ
    -0.08
    æĹĹèĪ°åºĹ
    -0.08
    åĬ
    -0.08
    æĹ·
    -0.08
    çıŃåŃIJ
    -0.08
     Silicon
    -0.08
    POSITIVE LOGITS
    åįıè®®
    0.14
    æĻ®åıĬ
    0.12
     protocol
    0.12
    çļĦä¸Ģç§į
    0.11
    ä¸Ģç§į
    0.11
    ä¸Ģ種
    0.11
    protocol
    0.11
    æĺ¯ä¸Ģç§į
    0.11
    æłĩåĩĨ
    0.11
     Protocol
    0.10
    Activations Density 0.432%

    No Known Activations