© 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. 60744
    Prev
    Next
    INDEX
    Explanations

    wandering, transient, aimless

    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
     اÙĦخبر
    -0.09
    inho
    -0.09
    avez
    -0.09
    .cond
    -0.09
    imers
    -0.09
    æį§
    -0.09
    OOM
    -0.08
    ERVE
    -0.08
    preh
    -0.08
    enha
    -0.08
    POSITIVE LOGITS
    ä¸įå®ī
    0.12
    ä¸į稳å®ļ
    0.12
    æµģ浪
    0.11
    ä¸įå®ļ
    0.10
    è§ħ
    0.10
    usercontent
    0.09
    æµģåĬ¨æĢ§
    0.09
    æĢ§å¼º
    0.09
    沿
    0.09
     lÃłnh
    0.09
    Activations Density 0.071%

    No Known Activations