© 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. 16848
    Prev
    Next
    INDEX
    Explanations

    contents of

    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
    ä¹ĭ称
    -0.10
    ourt
    -0.10
    /OR
    -0.10
    åĽŀå¤į
    -0.09
    geois
    -0.09
    æĤ¬æĮĤ
    -0.09
    æĤłæĤł
    -0.09
    缸符
    -0.09
    é£İåIJ¹
    -0.09
    æį¢æĿ¥
    -0.09
    POSITIVE LOGITS
     life
    0.09
    æľµ
    0.09
     merch
    0.08
    auf
    0.08
     жизни
    0.08
    xia
    0.08
    ause
    0.08
    åŀł
    0.08
    iom
    0.08
    æĩĤäºĭ
    0.08
    Activations Density 0.004%

    No Known Activations