© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29718
    Prev
    Next
    INDEX
    Explanations

    MEMS sensors

    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
    èĥ¸
    -0.09
    åľ¨åħ¨åĽ½
    -0.09
    åĬĪ
    -0.08
    åİļåİļçļĦ
    -0.08
    SAN
    -0.08
    è¤
    -0.08
    pard
    -0.08
     SCT
    -0.08
    gan
    -0.08
    æıIJæ¡Ī
    -0.08
    POSITIVE LOGITS
    读
    0.09
    个å¤ļ
    0.09
    mailbox
    0.09
    姿æĢģ
    0.09
    _registers
    0.09
    Registers
    0.09
     Registers
    0.09
    åħ¸èĮĥ
    0.09
     attitude
    0.08
    regon
    0.08
    Activations Density 0.129%

    No Known Activations