© 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. 5129
    Prev
    Next
    INDEX
    Explanations

    encompass / encompasses

    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
    OCUS
    -0.10
     اÙĦأساس
    -0.09
    à¸IJาà¸Ļ
    -0.09
    appoint
    -0.09
    æľºåħ³
    -0.09
    æ¯ĶèµĽä¸Ń
    -0.09
    loyd
    -0.09
    â½´
    -0.08
    omin
    -0.08
    表æĥħ
    -0.08
    POSITIVE LOGITS
     encompass
    0.14
    涵çĽĸ
    0.13
    åĽĬ
    0.13
    èĮĥåĽ´
    0.13
    åĮħ容
    0.12
    åľ¨åĨħçļĦ
    0.12
     encompasses
    0.11
    涵çĽĸäºĨ
    0.11
    æĭ¬
    0.10
    è¦ĨçĽĸéĿ¢
    0.10
    Activations Density 0.063%

    No Known Activations