© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 11303
    Prev
    Next
    INDEX
    Explanations

    sales tax, income tax, property tax

    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
    驼
    -0.11
    æīįå¹²
    -0.10
    ç»°
    -0.10
    éĢĶå¾Ħ
    -0.09
    æīįæľī
    -0.09
    便æį·
    -0.09
    awah
    -0.09
    åIJĮè¡Į
    -0.09
    amped
    -0.09
    çݰçĬ¶
    -0.09
    POSITIVE LOGITS
     PIT
    0.10
     tax
    0.09
    ç¨İ
    0.09
    uci
    0.09
    轺
    0.09
    cci
    0.09
    å²Ĺ
    0.09
     taxes
    0.09
    ony
    0.09
    è¢ĸ
    0.09
    Activations Density 0.037%

    No Known Activations