© 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. 20610
    Prev
    Next
    INDEX
    Explanations

    county-related offices and positions

    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
    åī¯å¸Ĥéķ¿
    -0.11
    åĽ½åº¦
    -0.10
    é³į
    -0.10
    æľŁåĨħ
    -0.10
    åŁİ管
    -0.10
    åĪ¨
    -0.09
    åħ¬åı¸ç«łç¨ĭ
    -0.09
    ÙĥÙĨ
    -0.09
    åİĤåĮº
    -0.09
    åī¯ä¹¦è®°
    -0.08
    POSITIVE LOGITS
    wide
    0.18
    å§Ķåī¯ä¹¦è®°
    0.12
    enance
    0.12
    cle
    0.11
    è¡Ļ
    0.11
    -wide
    0.10
    rary
    0.10
    aleb
    0.10
    -level
    0.10
    ستاÙĨ
    0.10
    Activations Density 0.045%

    No Known Activations