© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9188
    Prev
    Next
    INDEX
    Explanations

    school associations and districts

    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
    æł¡åĮº
    -0.10
    æİĴ污
    -0.10
    æijĬ
    -0.09
    æĥ³äºĨ
    -0.09
    æŀģåħ·
    -0.09
    梦
    -0.08
    æ¤ħ
    -0.08
    ikt
    -0.08
    ToUpper
    -0.08
    ä¸ĢåĽ¢
    -0.08
    POSITIVE LOGITS
    åħ¨çľģ
    0.11
     statewide
    0.10
    åIJĦåİ¿
    0.10
    åĵī
    0.09
    chemas
    0.09
     EntityState
    0.08
    çľģåħ¬å®īåİħ
    0.08
    溱
    0.08
    ugu
    0.08
    åIJ®
    0.08
    Activations Density 0.038%

    No Known Activations