© 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. 40073
    Prev
    Next
    INDEX
    Explanations

    pursue advanced degrees or careers

    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
    ervo
    -0.09
    人æ°ijæľįåĬ¡
    -0.08
    oter
    -0.08
    cobra
    -0.08
    ãĤĥ
    -0.08
    rox
    -0.08
    shoot
    -0.08
    ras
    -0.08
    æ¶Į
    -0.08
    raf
    -0.08
    POSITIVE LOGITS
    é¬ĥ
    0.10
    娼
    0.09
    åįģå¤ļ
    0.09
    æѤäºĭ
    0.09
    ick
    0.09
    åĿ³
    0.09
    髯
    0.09
    aget
    0.09
     mayor
    0.08
    /topics
    0.08
    Activations Density 0.005%

    No Known Activations