© 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. 21221
    Prev
    Next
    INDEX
    Explanations

    corporate position or entity

    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
    reff
    -0.10
    æ¦Ń
    -0.09
    身å¿ĥ
    -0.08
     Ale
    -0.08
    ODE
    -0.08
    ÑĤÑĮ
    -0.08
     Convenience
    -0.08
    ä»Ļ女
    -0.08
    ç©·
    -0.08
    eners
    -0.08
    POSITIVE LOGITS
    åĴĮ个人
    0.11
    æıĸ
    0.10
    çī¹ä»·
    0.10
    ìŀĶ
    0.09
    å¹´æĬ¥
    0.09
    å®ŀéªĮ室
    0.09
    çłĶåıijæĬķåħ¥
    0.09
    大éģĵ
    0.09
    èĭ¥æĤ¨
    0.09
    çĻ½é¢Ĩ
    0.09
    Activations Density 0.044%

    No Known Activations