© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3037
    Prev
    Next
    INDEX
    Explanations

    money and taxpayer expenditures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    immer
    -0.29
    âĨĻ
    -0.25
     rhythm
    -0.25
    åĻį
    -0.24
    æľīä¿¡å¿ĥ
    -0.24
    junction
    -0.24
    çݳ
    -0.24
     synthesis
    -0.23
    çļĦä¿¡å¿ĥ
    -0.23
     BaÅŁ
    -0.23
    POSITIVE LOGITS
    èĢĹè´¹
    0.35
     expensive
    0.35
     taxpayer
    0.34
    èĬ±è´¹
    0.34
    ä¸įå¿ħè¦ģçļĦ
    0.33
    æĺĤè´µ
    0.32
     expenditures
    0.32
    è´¹çĶ¨
    0.31
    å¼ĢæĶ¯
    0.31
     expenses
    0.31
    Activations Density 0.065%

    No Known Activations