© 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. 12146
    Prev
    Next
    INDEX
    Explanations

    satellite navigation

    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
    åıµ
    -0.08
     dro
    -0.08
    é£ĺ
    -0.08
    æĤļ
    -0.08
     Desert
    -0.08
    èIJ§
    -0.08
     cup
    -0.08
     reinst
    -0.08
    çĶ·å£«
    -0.08
    æ²Ļæ¼ł
    -0.08
    POSITIVE LOGITS
    身穿
    0.10
     Sleeve
    0.09
    Retail
    0.09
    ÑģеÑĤ
    0.09
    åĽ½åĢº
    0.09
    宫
    0.09
    ENTA
    0.08
    ollah
    0.08
    retch
    0.08
    MLE
    0.08
    Activations Density 0.131%

    No Known Activations