© 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. 11658
    Prev
    Next
    INDEX
    Explanations

    magnetic resonance imaging

    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
     пÑĢид
    -0.10
    ream
    -0.09
    aged
    -0.09
    irst
    -0.09
    OUS
    -0.08
    Ñīен
    -0.08
    ç³Ļ
    -0.08
    éĶ·
    -0.08
    ä¿©
    -0.08
    ëģĶ
    -0.08
    POSITIVE LOGITS
    åĽ¾çĶ»
    0.08
    Listen
    0.08
    好çľĭ
    0.08
    anel
    0.08
    æĹ¥æ¶Īæģ¯
    0.08
    ord
    0.08
    åįģä¸ĩ
    0.08
    å¤ļéĩį
    0.08
    agna
    0.08
    è¿Ļ个ä¸ĸçķĮ
    0.08
    Activations Density 0.053%

    No Known Activations