© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6468
    Prev
    Next
    INDEX
    Explanations

    aspects of various subjects

    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
    åŃĹåı·
    -0.09
    รà¸Ńย
    -0.09
     CENTER
    -0.09
    çĶ¥
    -0.08
    çĪ½
    -0.08
    éĻ·
    -0.08
    ç¾Ĭ
    -0.08
    statt
    -0.08
    ä¿Ĭ
    -0.08
    æ¸Ľ
    -0.08
    POSITIVE LOGITS
     aspects
    0.20
     aspect
    0.16
    aspect
    0.16
     facets
    0.14
    _aspect
    0.13
    pects
    0.13
    æĸ¹éĿ¢
    0.13
    åĽĽä¸ªæĸ¹éĿ¢
    0.13
    ä¸ī个æĸ¹éĿ¢
    0.12
    æĸ¹éĿ¢çļĦ
    0.12
    Activations Density 0.104%

    No Known Activations