© 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. 56341
    Prev
    Next
    INDEX
    Explanations

    represents, reflects, affects, describes

    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
    æĴ©
    -0.10
    Reviewer
    -0.09
    æł¼
    -0.09
    æĬĬèĩªå·±çļĦ
    -0.08
     Aren
    -0.08
    寸
    -0.08
    ä»Ģä¹Īåľ°æĸ¹
    -0.08
    磨
    -0.08
    æİ°
    -0.08
    egration
    -0.08
    POSITIVE LOGITS
    ä¸Ģå®ļèĥ½
    0.10
    èĽ®
    0.09
    éĺ²çĽĹ
    0.09
    _extent
    0.09
    æ»ļåĬ¨
    0.09
    å¨ģåIJį
    0.09
    าย
    0.08
     tÃŃn
    0.08
    ä»İ严治
    0.08
    为æѤ
    0.08
    Activations Density 0.004%

    No Known Activations