© 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. 6037
    Prev
    Next
    INDEX
    Explanations

    Michael Vick

    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
    лаÑģ
    -0.10
    ç¾İ女
    -0.09
    æĿijæ°ij们
    -0.09
    egg
    -0.09
    åŀł
    -0.09
    OrUpdate
    -0.09
     viá»ĩc
    -0.08
    .viewDidLoad
    -0.08
    ../../../
    -0.08
    ungen
    -0.08
    POSITIVE LOGITS
    è¿Ł
    0.09
    å»ī
    0.08
    ãĥ¼ãĤ¹
    0.08
    åIJĪæ³ķæĿĥçĽĬ
    0.08
    cke
    0.08
    adders
    0.08
    èĬ°
    0.08
    å®Ļ
    0.07
     LSM
    0.07
    æĸ¯çī¹
    0.07
    Activations Density 0.002%

    No Known Activations