© 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. 684
    Prev
    Next
    INDEX
    Explanations

    provided actions and responsibilities

    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
    Negative Logits
    æĺİæĻº
    -0.11
    esti
    -0.09
     пÑĢоÑģ
    -0.09
    cker
    -0.09
    åıĹåĪ°äºĨ
    -0.08
     поÑģл
    -0.08
    ahi
    -0.08
    æľīåı¯èĥ½
    -0.08
    alion
    -0.08
    iry
    -0.08
    POSITIVE LOGITS
    èĩªæľī
    0.10
    ç»Ļåĩº
    0.10
    ä¸ĢåĪĩéĥ½
    0.09
    å²ĺ
    0.09
    provided
    0.09
    å²Ľ
    0.09
    phasis
    0.09
     provided
    0.09
    æıIJä¾ĽçļĦ
    0.09
    ä¸ĭçıŃ
    0.09
    Activations Density 0.046%

    No Known Activations