© 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. 49665
    Prev
    Next
    INDEX
    Explanations

    microwave assisted synthesis

    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
    ç»ĩ
    -0.10
    ç¾½æ¯Ľ
    -0.09
    elib
    -0.09
    绸
    -0.09
    级åĪ«çļĦ
    -0.09
    榨
    -0.09
    æ°Ķåij³
    -0.09
    åľ»
    -0.09
    èģ¿
    -0.09
    ç²
    -0.09
    POSITIVE LOGITS
    anko
    0.09
    çľ¼åīį
    0.08
    çĶŁæŃ»
    0.08
     Graz
    0.08
    æ¡¥
    0.08
    è´´
    0.08
     vo
    0.08
     Hamp
    0.08
     DIRECT
    0.08
    IZER
    0.08
    Activations Density 0.036%

    No Known Activations